US20100295854A1 - Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery - Google Patents
Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery Download PDFInfo
- Publication number
- US20100295854A1 US20100295854A1 US12/635,999 US63599909A US2010295854A1 US 20100295854 A1 US20100295854 A1 US 20100295854A1 US 63599909 A US63599909 A US 63599909A US 2010295854 A1 US2010295854 A1 US 2010295854A1
- Authority
- US
- United States
- Prior art keywords
- representation
- source
- projection
- avatar
- deformation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/647—Three-dimensional objects by matching two-dimensional images to three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/28—Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/772—Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Definitions
- the present invention relates to object modeling and matching systems, and more particularly to the generation of a three-dimensional model of a target object from two- and three-dimensional input.
- a three-dimensional (3D) model of an object In many situations, it is useful to construct a three-dimensional (3D) model of an object when only a partial description of the object is available. In a typical situation, one or more two-dimensional (2D) images of the 3D object may be available, perhaps photographs taken from different viewpoints.
- a common method of creating a 3D model of a multi-featured object is to start with a base 3D model which describes a generic or typical example of the type of object being modeled, and then to add texture to the model using one or more 2D images of the object.
- a 3D “avatar” i.e., an electronic 3D graphical or pictorial representation
- a 3D “avatar” i.e., an electronic 3D graphical or pictorial representation
- mapping onto the model a texture from one or more 2D images of the face See U.S. Pat. No. 6,532,011 B1 to Francini et al., and U.S. Pat. No. 6,434,278 B1 to Hashimoto.
- the main problem with this approach is that the 3D geometry is not highly defined or tuned for the actual target object which is being generated.
- a common variant of the above approach is to use a set of 3D base models and select the one that most resembles the target object before performing the texture mapping step.
- a single parameterized base model is used, and the parameters of the model are adjusted to best approximate to the target. See U.S. Pat. No. 6,556,196 B1 to Blanz et al. These methods serve to refine the geometry to make it fit the target, at least to some extent. However, for any target object with a reasonable range of intrinsic variability, the geometry of the model will still not be well tuned to the target. This lack of geometric fit will detract from the verisimilitude of the 3D model to the target object.
- the present invention provides an automated method and system for generating an optimal 3D model of a target multifeatured object when only partial source data describing the object is available.
- the partial source data often consists of one or more 2D projections of the target object or an obscuration of a single projection, but may also include 3D data, such as from a 3D camera or scanner.
- the invention uses a set of reference 3D representations that span, to the extent practicable. the variations of the class of objects to which the target object belongs.
- the invention may automatically identify feature items common to the source data and to the reference representations, and establish correspondences between them.
- the system may identify points at the extremities of the eyes and mouth, or the nose profile, and establish correspondences between such features in the source data and in the reference representations. Manual identification and matching of feature items can also be incorporated if desired.
- all possible positions (i.e., orientations and translations) for each 3D reference representation are searched to identify the position and reference representation combination whose projection most closely matches the source data. The closeness of match is determined by a measure such as the minimum mean-squared error (MMSE) between the feature items in the projection of the 3D representation, and the corresponding feature items in the source projection.
- MMSE minimum mean-squared error
- a comparison is performed in 3D between the estimated deprojected positions of the feature items from the 2D source projection and the corresponding feature items of the 3D representation.
- the closest-fitting 3D reference representation may then be deformed to optimize the correspondence with the source projection.
- Each point in the mesh which defines the geometry of the 3D representation is free to move during the deformation.
- the search for the best-fitting position i.e., orientation and translation
- the geometry of the 3D model is tailored to the target object in two ways.
- the invention requires no information about the viewpoint from which the 2D source projection was captured, because a search is performed over all possible viewpoints, and the viewpoint is taken to be that which corresponds to the closest fit between the projected 3D representation and the 2D source data.
- the invention comprises a method of comparing at least one source 2D projection of a source multifeatured object to a reference library of 3D reference objects.
- a plurality of reference 3D representations of generically similar multifeatured objects is provided, and a viewpoint-invariant search of the reference 3D representations is performed to locate the reference 3D representation having a 2D projection most resembling the source projection(s).
- resemblance is determined by a degree of alignment between feature items in the 3D representation and corresponding feature items in the source 2D projection(s).
- Each reference 3D representation may be searched over a range of possible 2D projections of the 3D representation without actually generating any projections.
- the search over a range of possible 2D projections may comprise computing a rigid motion of the reference 3D representation optimally consistent with a viewpoint of the source multifeatured object in at least one of the 2D projections.
- the rigid motions may comprise pitch, roll, yaw, and translation in three dimensions.
- Automatic camera calibration may be performed by estimation of camera parameters, such as aspect ratio and field of view, from image landmarks.
- the optimum rigid motion may be determined by estimating a conditional mean pose or geometric registration as it relates to feature items comprising points, curves, surfaces, and subvolumes in a 3D coordinate space associated with the reference 3D representation such that the feature items are projectionally consistent with feature items in source 2D projection(s).
- MMSE estimates between the conditional mean estimate of the projected feature items and corresponding feature items of the reference 3D representation are generated.
- the rigid motion may be constrained by known 3D position information associated with the source 2D projection(s).
- the feature items may include curves as well as points which are extracted from the source projection using dynamic programming. Further, areas as well as surfaces and or subvolumes may be used as features generated via isocontouring (such as via the Marching Cubes algorithm) or automated segmentation algorithms.
- the feature items used in the matching process may be found automatically by using correspondences between the 2D source projection(s) and projected imagery of at least one reference 3D object.
- the invention may further comprise the step of creating a 3D representation of the source 2D projection(s) by deforming the located (i.e., best-fitting) reference 3D representation so as to resemble the source multifeatured object.
- the deformation is a large deformation diffeomorphism, which serves to preserve the geometry and topology of the reference 3D representation.
- the deformation step may deform the located 3D representation so that feature items in the source 2D projection(s) align with corresponding features in the located reference 3D representation.
- the deformation step may occur with or without rigid motions and may include affine motions.
- the deformation step may be constrained by at least one of known 3D position information associated with the source 2D projection(s), and 3D data of the source object.
- the deformation may be performed using a closed form expression.
- the invention comprises a system for comparing at least one source 2D projection of a source multifeatured object to a reference library of 3D reference objects.
- the system comprises a database comprising a plurality of reference 3D representations of generically similar multifeatured objects and an analyzer for performing a viewpoint-invariant search of the reference 3D representations to locate the reference 3D representation having a 2D projection most resembling the source projection(s).
- the analyzer determines resemblance by a degree of alignment between feature items in the 3D representation and corresponding feature items in the source 2D projection(s).
- the analyzer may search each reference 3D representation over a range of possible 2D projections of the 3D representation without actually generating any projections.
- the analyzer searches over a range of possible 2D projections by computing a rigid motion of the reference 3D representation optimally consistent with a viewpoint of the source multifeatured object in at least one of the 2D projections.
- the rigid motions may comprise pitch, roll, yaw, and translation in three dimensions.
- the analyzer may be configured to perform automatic camera calibration by estimating camera parameters. such as aspect ratio and field of view, from image landmarks.
- the analyzer is configured to determine the optimum rigid motion by estimating a conditional mean of feature items comprising points, curves, surfaces, and subvolumes in a 3D coordinate space associated with the reference 3D representation such that the feature items are projectionally consistent with feature items in the source 2D projection(s).
- the analyzer is further configured to generate MMSE estimates between the conditional mean estimate of the projected feature items and corresponding feature items of the reference 3D representation.
- the rigid motion may be constrained by known 3D position information associated with the source 2D projection(s).
- the analyzer is configured to extract feature items from the source projection using dynamic programming. In further embodiments, the analyzer may be configured to find feature items used in the matching process automatically by using correspondences between source imagery and projected imagery of at least one reference 3D object.
- the invention may further comprise a deformation module for creating a 3D representation of the at least one source 2D projection by deforming the located (i.e., best-fitting) reference 3D representation so as to resemble the source multifeatured object.
- the deformation module deforms the located reference 3D representation using large deformation diffeomorphism, which serves to preserve the geometry and topology of the reference 3D representation.
- the deformation module may deform the located 3D representation so that feature items in the source 2D projection(s) align with corresponding features in the located reference 3D representation.
- the deformation module may or may not use rigid motions and may use affine motions.
- the deformation module may be constrained by at least one of known 3D position information associated with the source 2D projection(s) and 3D data of the source object.
- the deformation module may operate in accordance with a closed form expression.
- the invention comprises a method of comparing a source 3D object to at least one reference 3D object.
- the method involves creating 2D representations of the source object and the reference object(s) and using projective geometry to characterize a correspondence between the source 3D object and a reference 3D object.
- the correspondence may be characterized by a particular viewpoint for the 2D representation of the 3D source object.
- the invention comprises a system for comparing a source 3D object to at least one reference 3D object.
- the system comprises a projection module for creating 2D representations of the source object and the reference object(s) and an analyzer which uses projective geometry to characterize a correspondence between the source 3D object and a reference 3D object.
- the above described methods and systems are used for the case when the 3D object is a face and the reference 3D representations are avatars.
- the invention comprises a method for creating a 3D representation from at least one source 2D projection of a source multifeatured object.
- at least one reference 3D representation of a generically similar object is provided, one of the provided representation(s) is located, and a 3D representation of the source 2D projection(s) is created by deforming the located reference representation in accordance with the source 2D projection(s) so as to resemble the source multifeatured object.
- the source 2D projection(s) is used to locate the reference representation.
- the set of reference representations includes more than one member, and the reference most resembling the source 2D projection(s) is located by performing a viewpoint-invariant search of the set of reference representations, without necessarily actually generating any projections.
- the search may include computing a rigid motion of the reference representation optimally consistent with a viewpoint of the source multifeatured object in at least one of the source projections.
- a 3D representation of the source projection(s) is created by deforming the located reference representation so as to resemble the source multifeatured object.
- the deformation may be a large deformation diffeomorphism.
- the deformation deforms the located reference so that feature items in the source projection(s) align with corresponding feature items in the located 3D reference representation.
- the deformation is performed in real time.
- the invention comprises a system for creating a 3D representation from at least one source 2D projection of a source multifeatured object.
- the system includes a database of at least one reference 3D representation of a generically similar object, and an analyzer for locating one of the provided representation(s).
- the system further includes a deformation module for creating a 3D representation of the source 2D projection(s) by deforming the located reference representation in accordance with the source 2D projection(s) so as to resemble the source multifeatured object.
- the analyzer uses the source 2D projection(s) to locate the reference representation.
- the set of reference representations includes more than one member, and the analyzer locates the reference most resembling the source 2D projection(s) by performing a viewpoint-invariant search of the set of reference representations, without necessarily actually generating any projections.
- the search may include computing a rigid motion of the reference representation optimally consistent with a viewpoint of the source multi featured object in at least one of the source projections.
- the deformation module creates a 3D representation of the source projection(s) by deforming the located reference representation so as to resemble the source multifeatured object.
- the deformation may be a large deformation diffeomorphism.
- the deformation module deforms the located reference so that feature items in the source projection(s) align with corresponding feature items in the located 3D reference representation.
- the deformation module operates in real time.
- FIG. 1 schematically illustrates the various components of the invention, starting with the target object, the reference objects, and yielding an optimal 3D model after performing a search and deformation.
- FIGS. 2A , 2 B, and 2 C schematically illustrate the components of a 3D avatar.
- FIG. 3 schematically illustrates the matching of feature items in the 2D imagery.
- FIG. 4 is a block diagram showing a representative hardware environment for the present invention.
- FIG. 5 is a block diagram showing components of the analyzer illustrated in FIG. 4 .
- FIG. 6 is a block diagram showing the key functions performed by the analyzer.
- FIG. 1 illustrates the basic operation of the invention in the case where the 3D target multifeatured object is a face and the set of reference 3D representations are avatars.
- the matching process starts with a set of reference 3D avatars which represent, to the extent practicable, the range of different types of heads to be matched.
- the avatars may include faces of men and women, faces with varying quantities and types of hair, faces of different ages, and faces representing different races.
- the reference set includes numerous (e.g., several hundred or more) avatars, though the invention works with as few as one reference object, and as many for which storage space and compute time are available. In some situations, only a single reference avatar will be used.
- the source data of the target face is illustrated as a single 2D photograph of the target 3D face taken from an unknown viewpoint.
- selected features to be used for matching are identified in the source photograph.
- the features may be points, such as the extremities of the mouth and eyes, or curves representing a profile, an eyebrow, or other distinctive curve, or subareas such as an eyebrow, nose or cheek.
- the corresponding features are identified in the reference avatars.
- the selection of features in the target photograph, and the identification of corresponding features in the reference avatars may be done automatically according to the invention.
- FIG. 1 illustrates the best-fitting reference avatar to be the middle one.
- the best reference avatar is deformed to match the target photograph more closely.
- the features of the photograph are reverse projected to the coordinates of the best reference avatar in the orientation and position corresponding to the best match.
- the mesh points of the avatar are then deformed in 3D to minimize the distances between the reverse-projected features of the photograph and the corresponding avatar features.
- the avatar resulting from this deformation will be a closer approximation to the target 3D face.
- the rigid motion search and deformation steps may be repeated iteratively, e.g., until the quality of fit no longer improves appreciably.
- the resulting 3D model is the optimal match to the target face.
- the invention can be used effectively even when the source imagery includes only a part of the target face, or when the target face is partially obscured, such as, for example, by sunglasses or facial hair.
- the approach of the invention is suitable for any multifeatured object, such as faces, animals, plants, or buildings. For ease of explanation, however, the ensuing description will focus on faces as an exemplary (and non-limiting) application.
- FIGS. 2A , 2 B, and 2 C show the components of a representative avatar.
- the geometry of the avatar is represented by a mesh of points in 3D which are the vertices of set of triangular polygons approximating the surface of the avatar.
- FIG. 2A illustrates a head-on view 202 and a side view 204 of the triangular polygon representation.
- each vertex is given a color value, and each triangular face may be colored according to an average of the color values assigned to its vertices.
- the color values are determined from a 2D texture map 206 , illustrated in FIG. 2B , which may be derived from a photograph.
- FIG. 2D texture map 206 illustrated in FIG. 2B , which may be derived from a photograph.
- the final avatar with texture is illustrated in a head-on view 208 and side view 210 .
- the avatar is associated with a coordinate system which is fixed to it, and is indexed by three angular degrees of freedom (pitch, roll, and yaw), and three translational degrees of freedom of the rigid body center in three-space.
- individual features of the avatar such as the chin, teeth and eyes may have their own local coordinates (e.g., chin axis) which form part of the avatar description.
- the present invention may be equally applied to avatars for which a different data representation is used.
- texture values may be represented as RGB values, or using other color representations, such as HSL.
- the data representing the avatar vertices and the relationships among the vertices may vary.
- the mesh points may be connected to form non-triangular polygons representing the avatar surface.
- the invention may include a conventional rendering engine for generating 2D imagery from a 3D avatar.
- the rendering engine may be implemented in OpenGL, or in any other 3D rendering system, and allows for the rapid projection of a 3D avatar into a 2D image plane representing a camera view of the 3D avatar.
- the rendering engine may also include the specification of the avatar lighting, allowing for the generation of 2D projections corresponding to varying illumination of the avatar. Lighting corresponding to a varying number of light sources of varying colors, intensities, and positions may be generated.
- the feature items in the 2D source projection which are used for matching are selected by hand or via automated methods. These items may be points or curves.
- suitable points may be inflection points at the lips, points on the eyebrows, points at the extremities of the eyes, or extremities of nostrils, and suitable curves may include an eyebrow or lip.
- the source projection includes a side view, the feature points corresponding to the profile are used and may include the tip of the nose or chin.
- Suitable feature item curves may include distinct parts of the profile, such as nose, forehead, or chin.
- a user interface is provided which allows the user to identify feature points individually or to mark groups of points delineated by a spline curve, or to select a set of points forming a line.
- the automated detection of feature items on the 2D source projection is performed by searching for specific features of a face, such as eyeballs, nostrils, and lips.
- the approach may use Bayesian classifiers and decision trees in which hierarchical detection probes are built from training data generated from actual avatars.
- the detection probes are desirably stored at multiple pixel scales so that the specific parameters, such as for orientation of a feature, are only computing on finer scales if the larger-scale probes yield a positive detection.
- the feature detection probes may be generated from image databases representing large numbers of individuals who have had their features demarcated and segregated so that the detection probes become specifically tuned to these features.
- the automated feature detection approach may use pattern classification, Bayes nets, neural networks, or other known techniques for determining the location of features in facial images.
- the automated detection of curve features in the source projection may use dynamic programming approaches to generate curves from a series of points so as to reduce the amount of computation required to identify an optimal curve and maximize a sequentially additive cost function.
- a cost function represents a sequence of features such as the contrast of the profile against background, or the darkness of an eyebrow, or the crease between lips.
- a path of N points can be thought of as consisting of a starting node x 0 and a set of vectors v 0 , v 1 , . . . , v N ⁇ 1 connecting neighboring nodes. The nodes comprising this path are defined as
- dynamic programming may be used to generate maximum (or minimum) cost paths. This reduces the complexity of the algorithm from K N to NK 2 where N is the length of a path and K is the total number of nodes, as dynamic programming takes advantage of the fact that the cost is sequentially additive, allowing a host of sub-optimal paths to be ignored. Dynamic programming techniques and systems are well-characterized in the art and can be applied as discussed herein without undue experimentation.
- the 3D rotation and translation from the avatar coordinates to the source projection is determined. This corresponds to finding the viewpoint from which the source projection was captured. In preferred embodiments, this is achieved by calculating the position of the avatar in 3D space that best matches the set of selected feature items in the 2D source projection. Generally, these feature items will be points, curves, or subareas and the source projection will be a photograph on which the position of these items can be measured, either manually or automatically.
- the position calculation may be based on the computation of the conditional mean estimate of the reverse projection positions in 3D of the 2D feature items, followed by the computation of MMSE estimates for the rotation and translation parameters in 3D, given the estimates of the 3D positions of the feature items.
- the MMSE estimate for translation position is closed form; when substituted back into the squared error function, it gives an explicit function in terms of only the rotations. Since the rotations are not vector parameters, they may be calculated using non-linear gradient descent through the tangent space of the group or via local representation using the angular velocities of the skew-symmetric matrices.
- the distance metrics used to measure the quality of fit between the reverse projections of feature items from the source imagery and corresponding items in the 3D avatar may be, for example, Poisson or other distance metrics which may or may not satisfy the triangle inequality.
- the feature item matching may be performed directly, without the intermediate step of calculating the conditional mean estimate of the deprojected 2D features.
- the cost function used for positioning the 3D avatar can be minimized using algorithms such as closed form quadratic optimization, iterative Newton descent or gradient methods.
- the 3D positioning technique is first considered without deformation of the reference avatar.
- a 3D reference avatar is referred to as a CAD (computer-aided design) model, or by the symbol CAD.
- the projective geometry mapping is defined as either positive or negative z, i.e., projection occurs along the z axis. In all the projective geometry
- p j ( ⁇ 1 ⁇ x j - z j , ⁇ 2 ⁇ y j - z j ) ,
- the norm has within it a 3 ⁇ 3 matrix which represents this variability in the norm.
- the optimum rotation and translation may next be estimated from feature points.
- some information about the position of the object in 3D space is known.
- the position from a previous image may be available.
- the rotation/translation data may be indexed in many different ways. For example, to index according to the rotation around the center of the object, rather than fixed external world coordinates, the coordinates are just reparameterized by defining a ⁇ tilde over (x) ⁇ x ⁇ x c . All of the techniques described herein remain the same.
- the preferred 3D algorithm for rigid motion efficiently changes states of geometric pose for comparison to the measured imagery.
- the preferred 3D algorithm for diffeomorphic transformation of geometry matches the geometry to target 2D image features. It should be understood, however, that other methods of performing the comparison of the 3D representation to the source imagery may be used, including those that do not make use of specific image features.
- the 3D avatar may be deformed in order to improve its correspondence with the source imagery.
- the allowed deformations are generally limited to diffeomorphisms of the original avatar. This serves to preserve the avatar topology, guaranteeing that the result of the deformation will be a face.
- the deformations may also enforce topological constraints, such as the symmetry of the geometry. This constraint is especially useful in situations where parts of the source object are obscured, and the full geometry is inferred from partial source information.
- FIGS. 3A and 3B illustrate the effect of avatar deformation on the matching of the avatar to the source imagery.
- feature points are shown as black crosses on the source image 302 .
- An example is the feature point at the left extremity of the left eyebrow 304 .
- the projections of the corresponding feature points belonging to the best-matching reference avatar with optimal rigid motion prior to deformation are shown as white crosses. It can be seen that the projected point corresponding to the left extremity of the left eyebrow 306 is noticeably displaced from its counterpart 304 .
- FIG. 3B the same source image 302 is shown with feature points again indicated by black crosses. This time, the best-fitting avatar feature points shown as white crosses are now projected after deformation.
- the correspondence between source feature points and avatar feature points is markedly improved, as shown, for example, by the improved proximity of the projected left eyebrow feature point 308 to its source counterpart 304 .
- the 3D avatar diffeomorphism calculation starts with the initial conditions for placement of the avatar determined by the feature item detection and computation of the best-fitting rigid motion and the original geometry of the avatar. It then proceeds by allowing all of the points on the avatar to move independently according to a predefined formula to minimize the distance between the deformed avatar points in 3D and the conditional mean estimates of the 2D landmark points reverse projected to the 3D coordinates. Once this diffeornorphism is calculated, the 3D landmark rigid motion algorithm is applied again to the source projections and feature items to find the best guess of the camera positions given this newly transformed avatar with its new vertex positions. Subsequently, a new diffeomorphism is generated, and this process is continued until it converges.
- iteration may not be used, with the rigid motion calculation being performed only a single time, and just one diffeomorphism transformation applied.
- camera orientations i.e., the viewpoint of the measured source projections
- these can be used as fixed inputs to the calculation, with no rigid transformation required.
- n is cotangent of the angle
- w,h are aspect ratio widths and heights
- p j ( ⁇ 1 ⁇ x j z j , ⁇ 2 ⁇ y j z j ) .
- the goal is to construct the deformation of the CAD model x ⁇ x+u(x), x ⁇ CAD with unknown camera rigid motions corresponding to the measured projective image feature items.
- the projective points for each orientation v 1, . . . , V, and smoothing matrices
- the avatar may be deformed with small deformations only and no rigid motions.
- the measured feature items are all points from a single camera viewing which generated the projected source image in which the feature points were measured.
- the goal is to construct the deformation of the CAD model constructing the mapping x ⁇ x+u(x), x ⁇ CAD:
- diffeomorphic deformations with no rigid motions of the avatar are applied.
- the deformation of the CAD model constructing the mapping x ⁇ (x), x ⁇ CAD is constructed:
- mappings are repeatedly generated from the new vector field by running an iterative algorithm until convergence:
- the deformation may be performed in real time for the case when the rigid motions (i.e., the rotation/translation) which bring the avatar into correspondence with the one or more source 2D projection are not known.
- the rigid motions i.e., the rotation/translation
- a similar approach to the one above is used, with the addition of an estimation of the rigid motions using the techniques described herein.
- the initialization u new 0 is used.
- the avatar is deformed in real-time using diffeomorphic deformations.
- the solution to the real-time deformation algorithm generates a deformation which may be used as an initial condition for the solution of the diffeomorphic deformation.
- Real-time diffeomorphic deformation is accomplished by incorporating the real-time deformations solution as an initial condition and then performing a small number (in the region of 1 to 10) iterations of the diffeomorphic deformation calculation.
- the deformation may include affine motions.
- affine motion A x ⁇ Ax where A is the 3 ⁇ 3 generalized linear matrix so that
- both feature items in the projective imagery as well as the imagery itself can be used to drive the deformation of the avatar.
- Augmentation of source data to incorporate source imagery may improve the quality of the fit between the deformed avatar and the target face.
- one more term is added to the deformation techniques.
- the observed projective ⁇ (p) is an (R,G,B) vector and the projective matrix becomes
- the point x(p) being the revealed point which is not occluded (closest point to the projection on the ray) on the 3D CAD model which projects to the point p in the image plane.
- the projected template matrices resulting from finite differences on the (R,G,B) components at the projective coordinate p of the template value are required.
- the norm is interpreted componentwise:
- Equation ⁇ ⁇ 34 min u ⁇ - 2 ⁇ ⁇ p ⁇ [ 0 , 1 ] 2 ⁇ u ⁇ ( x ⁇ ( p ) ) t ⁇ I .
- image matching is performed directly on the source imagery or on the fundamental 3D volumes into which the source object can be divided.
- the measured target projective image has labeled points, curves, and subregions generated by diffeomorphic image matching.
- the projective exemplar can be transformed bijectively via the diffeomorphisms onto the target candidate photograph, thereby automatically labeling the target photographs into its constituent submanifolds.
- the template and target images I 0 , I 1 are transformed to satisfy
- the given diffeomorphism is applied to labeled points, curves, and areas in the template I 0 thereby labeling those points, curves, and areas in the target photograph.
- the diffeomorphisms are used to define bijective correspondence in the 3D background space, and the matching is performed in the volume rather than in the image plane.
- the avatar is deformed with small deformations only and no rigid motions.
- the measured feature items are all points from a single camera viewing which generated the projected source image in which the feature points were measured.
- the optimum selected avatar model is the one closest to the candidate in the metric. Any of a variety of distance functions may be used in the selection of the avatar, including the large deformation metric from the diffeomorphism mapping technique described above, the real-time metric described above.
- the CAD model is selected to minimize the metric based on one or several sets of features from photographs, here described for one photo:
- both metrics including unknown or known rigid motions, large deformation metrics, or affine motions can be used such as described in equations 28 and 29, respectively.
- the metric is selected which minimizes the distance between the measurements and the family of candidate CAD models.
- the K matrix defining the quadratic form metric measuring the distance is computed:
- K ( K ⁇ ( x 1 a , x 1 a ) Kx ⁇ ( 1 a ⁇ , x 2 a ) Kx 1 a , x N a ) ) ⁇ ⁇ ⁇ ⁇ K ⁇ ( x N a , x 1 a ) K ⁇ ( x N a , x 2 a ) Kx N a , x N a ) ; ( Equation ⁇ ⁇ 39 )
- the minimum none is determined by the error between the CAD model feature points and the photographic feature points.
- the present invention may also be used to match to articulated target objects.
- the diffeomorphism and real-time mapping techniques carry the template 3D representations bijectively onto the target models. carrying all of the information in the template.
- the template models are labeled with different regions corresponding to different components of the articulated object.
- the articulated regions may include teeth, eyebrows, eyelids, eyes, and jaw.
- Each of these subcomponents can be articulated during motion of the model according to an articulation model specifying allowed modes of articulation.
- the mapping techniques carry these triangulated subcomponents onto the targets, thereby labeling them with their subcomponents automatically.
- the resulting selected CAD model therefore has its constituent parts automatically labeled, thereby allowing each avatar to be articulated during motion sequences.
- the best matching rigid motion corresponds to:
- the real-time deformation corresponds to:
- the diffeomorphism deformation corresponds to with
- the techniques described herein also allow for the automated calibration camera parameters, such as the aspect ratio and field of view.
- p j ( x j ⁇ 2 ⁇ z j , y j z j ) .
- the calibration of the camera is determined under the assumption that there is no transformation (affine or other) of the avatar.
- the z value is parameterized by incorporating the n frustrum distance so that all depth coordinates are the above coordinates plus frustrum depth. Videos can show different aspect ratios
- FOV 2 ⁇ ⁇ tan - 1 ⁇ 1 a 1 .
- the techniques described herein may be used to compare a source 3D object to a single reference object.
- 2D representations of the source object and the reference object are created, and the correspondence between them is characterized using mathematical optimization and projective geometry.
- the correspondence is characterized by specifying the viewpoint from which the 2D source projection was captured.
- the system includes a video source 402 (e.g., a video camera or a scanning device) which supplies a still input image to be analyzed.
- the output of the video source 402 is digitized as a frame into an array of pixels by a digitizer 404 .
- the digitized images are transmitted along the system bus 406 over which all system components communicate, and may be stored in a mass storage device (such as a hard disc or optical storage unit) 408 as well as in main system memory 410 (specifically, within a partition defining a series of identically sized input image buffers) 412 .
- a mass storage device such as a hard disc or optical storage unit
- the operation of the illustrated system is directed by a central-processing unit (“CPU”) 414 .
- CPU central-processing unit
- the system preferably contains a graphics or image-processing board 416 ; this is a standard component well-known to those skilled in the art.
- the user interacts with the system using a keyboard 418 and a position-sensing device (e.g., a mouse) 420 .
- a position-sensing device e.g., a mouse
- the output of either device can be used to designate information or select particular points or areas of a screen display 420 to direct functions performed by the system.
- the main memory 410 contains a group of modules that control the operation of the CPU 414 and its interaction with the other hardware components.
- An operating system 424 directs the execution of low-level, basic system functions such as memory allocation, file management and operation of mass storage devices 408 .
- the analyzer 426 implemented as a series of stored instructions, directs execution of the primary functions performed by the invention, as discussed below: and instructions defining a user interface 428 allow straightforward interaction over screen display 422 .
- the user interface 428 generates words or graphical images on the display 422 to prompt action by the user, and accepts commands from the keyboard 418 and/or position-sensing device 420 .
- the memory 410 includes a partition 430 for storing for storing a database of 3D reference avatars, as described above.
- each image buffer 412 define a “raster,” i.e., a regular 2D pattern of discrete pixel positions that collectively represent an image and may be used to drive (e.g., by means of image-processing board 416 or an image server) screen display 422 to display that image.
- the content of each memory location in a frame buffer directly governs the appearance of a corresponding pixel on the display 422 .
- main memory 410 main memory 410
- modules of main memory 410 have been described separately, this is for clarity of presentation only; so long as the system performs all the necessary functions, it is immaterial how they are distributed within the system and the programming architecture thereof Likewise, though conceptually organized as grids, pixelmaps need not actually be stored digitally in this fashion. Rather, for convenience of memory utilization and transmission, the raster pattern is usually encoded as an ordered array of pixels.
- FIG. 5 illustrates the components of a preferred implementation of the analyzer 426 .
- the projection module 502 takes a 3D model and makes a 2D projection of it onto any chosen plane. In general, an efficient projection module 502 will be required in order to create numerous projections over the space of rotations and translations for each of the candidate reference avatars.
- the deformation module 504 performs one or more types of deformation on an avatar in order to make it more closely resemble the source object.
- the deformation is performed in 3D space, with every point defining the avatar mesh being free to move in order to optimize the fit to the conditional mean estimates of the reverse projected feature items from the source imagery. In general. deformation is only applied to the best-fitting reference object, if more than one reference object is supplied.
- the rendering module 506 allows for the rapid projection of a 3D avatar into 2D with the option of including the specification of the avatar lighting.
- the 2D projection corresponds to the chosen lighting of the 3D avatar.
- the feature detection module 508 searches for specific feature items in the 2D source projection.
- the features may include eyes, nostrils, lips, and may incorporate probes that operate at several different pixel scales.
- FIG. 6 illustrates the functions of the invention performed in main memory.
- the system examines the source imagery and automatically detects features of a face. such as eyeballs, nostrils, and lips that can be used for matching purposes, as described above.
- the detected feature items are reverse projected into the coordinate frame of the candidate avatar, as described above and using equation 7.
- the optimum rotation/translation of the candidate avatar is estimated using the techniques described above and using equations 8, 9 and 10.
- any prior information that may be available about the position of the source object with respect to the available 2D projections is added into the computation, as described herein using equations 1 1-13.
- this data is used to constrain the rigid motion search as shown in step 610 and as described above with reference to equations 41-43.
- the best-fitting avatar is selected in step 612 , as described above, with reference to equations 38-40. Subsequently, the best-fitting avatar located in step 612 is deformed in step 614 .
- 3D measurements of the source object 610 if any, are used to constrain the deformation 614 .
- portions of the source imagery 616 itself may be used to influence the deformation 614 .
- the invention provides for several different kinds of deformation which may be optionally applied to the best-fitting reference avatar in order to improve its correspondence with the target object.
- the deformations may include real-time deformation without rigid motions in which a closed form expression is found for the deformation, as described above using equations 18, 19.
- a diffeomorphic deformation of the avatar with no rigid motions may be applied (equations 22-24).
- a real time deformation with unknown rigid motion of the avatar may be deployed (equations 28, 29).
- a real-time diffeormorphic deformation may be applied to the avatar by iterating the real-time deformation.
- the avatar may be deformed using affine motions (equations 30, 31).
- the deformation of the avatar may be guided by matching a projection to large numbers of feature items in the source data, including the identification of submanifolds within the avatar, as described above with reference to equation 37.
- the deformations described above may be applied to each articulated component separately.
- the invention enables camera parameters, such as aspect ratio and field of view to be estimated as shown in step 618 and described above. with reference to equations 44-49.
- the invention is not limited to the matching of faces, but may be used for matching any multifeatured object using a database of reference 3D representations that correspond to the generic type of the target object to be matched.
Abstract
A method and system for characterizing features in a source multifeatured three-dimensional object and for locating a best-matching three-dimensional object from a reference database of such objects by performing a viewpoint invariant search among the reference objects. The invention further includes the creation of a three-dimensional representation of the source object by deforming a reference object.
Description
- This application claims priority to and the benefits of U.S. Provisional Applications Ser. Nos. 60/452,429, 60/452,430 and 60/452,431 filed on Mar. 6, 2003 (the entire disclosures of which are hereby incorporated by reference).
- The present invention relates to object modeling and matching systems, and more particularly to the generation of a three-dimensional model of a target object from two- and three-dimensional input.
- In many situations, it is useful to construct a three-dimensional (3D) model of an object when only a partial description of the object is available. In a typical situation, one or more two-dimensional (2D) images of the 3D object may be available, perhaps photographs taken from different viewpoints. A common method of creating a 3D model of a multi-featured object is to start with a
base 3D model which describes a generic or typical example of the type of object being modeled, and then to add texture to the model using one or more 2D images of the object. For example, if the multi-featured object is a human face, a 3D “avatar” (i.e., an electronic 3D graphical or pictorial representation) would be generated by using a pre-existing, standard 3D model of a human face, and mapping onto the model a texture from one or more 2D images of the face. See U.S. Pat. No. 6,532,011 B1 to Francini et al., and U.S. Pat. No. 6,434,278 B1 to Hashimoto. The main problem with this approach is that the 3D geometry is not highly defined or tuned for the actual target object which is being generated. - A common variant of the above approach is to use a set of 3D base models and select the one that most resembles the target object before performing the texture mapping step. Alternatively, a single parameterized base model is used, and the parameters of the model are adjusted to best approximate to the target. See U.S. Pat. No. 6,556,196 B1 to Blanz et al. These methods serve to refine the geometry to make it fit the target, at least to some extent. However, for any target object with a reasonable range of intrinsic variability, the geometry of the model will still not be well tuned to the target. This lack of geometric fit will detract from the verisimilitude of the 3D model to the target object.
- Conventional techniques typically also require that the 2D images being used for texturing the model be acquired from known viewpoints relative to the 3D object being modeled. This usually limits the use of such approaches to situations where the model is being generated in a controlled environment in which the target object can be photographed. Alternatively, resort may be had to human intervention to align 2D images to the 3D model to be generated. See U.S. Patent Publication No. 2002/0012454 to Liu et al. This manual step places a severe limit on the speed with which a 3D model can be generated from 2D imagery.
- Accordingly, a need exists for an automated approach that systematically makes use of available 2D source data for a 3D object to synthesize an optimal 3D model of the object.
- The present invention provides an automated method and system for generating an optimal 3D model of a target multifeatured object when only partial source data describing the object is available. The partial source data often consists of one or more 2D projections of the target object or an obscuration of a single projection, but may also include 3D data, such as from a 3D camera or scanner. The invention uses a set of
reference 3D representations that span, to the extent practicable. the variations of the class of objects to which the target object belongs. The invention may automatically identify feature items common to the source data and to the reference representations, and establish correspondences between them. For example, if the target object is a face the system may identify points at the extremities of the eyes and mouth, or the nose profile, and establish correspondences between such features in the source data and in the reference representations. Manual identification and matching of feature items can also be incorporated if desired. Next, all possible positions (i.e., orientations and translations) for each 3D reference representation are searched to identify the position and reference representation combination whose projection most closely matches the source data. The closeness of match is determined by a measure such as the minimum mean-squared error (MMSE) between the feature items in the projection of the 3D representation, and the corresponding feature items in the source projection. A comparison is performed in 3D between the estimated deprojected positions of the feature items from the 2D source projection and the corresponding feature items of the 3D representation. The closest-fitting 3D reference representation may then be deformed to optimize the correspondence with the source projection. Each point in the mesh which defines the geometry of the 3D representation is free to move during the deformation. The search for the best-fitting position (i.e., orientation and translation) is repeated using the deformed 3D representation, and the deformation and search may be repeated iteratively until convergence occurs or terminated at any time. - Thus the geometry of the 3D model is tailored to the target object in two ways. First, when more than one reference representation is available, the selection of the best-fitting reference representation from a set of references enables the optimal coarse-grain choice to be made. Second, deformation enables fine scale tuning in which errors introduced by inaccurate choice of viewpoint are progressively reduced by iteration. The invention requires no information about the viewpoint from which the 2D source projection was captured, because a search is performed over all possible viewpoints, and the viewpoint is taken to be that which corresponds to the closest fit between the projected 3D representation and the 2D source data.
- In a first aspect, the invention comprises a method of comparing at least one source 2D projection of a source multifeatured object to a reference library of 3D reference objects. In accordance with the method, a plurality of
reference 3D representations of generically similar multifeatured objects is provided, and a viewpoint-invariant search of thereference 3D representations is performed to locate thereference 3D representation having a 2D projection most resembling the source projection(s). In some embodiments, resemblance is determined by a degree of alignment between feature items in the 3D representation and corresponding feature items in the source 2D projection(s). Eachreference 3D representation may be searched over a range of possible 2D projections of the 3D representation without actually generating any projections. The search over a range of possible 2D projections may comprise computing a rigid motion of thereference 3D representation optimally consistent with a viewpoint of the source multifeatured object in at least one of the 2D projections. The rigid motions may comprise pitch, roll, yaw, and translation in three dimensions. Automatic camera calibration may be performed by estimation of camera parameters, such as aspect ratio and field of view, from image landmarks. - In some embodiments, the optimum rigid motion may be determined by estimating a conditional mean pose or geometric registration as it relates to feature items comprising points, curves, surfaces, and subvolumes in a 3D coordinate space associated with the
reference 3D representation such that the feature items are projectionally consistent with feature items in source 2D projection(s). MMSE estimates between the conditional mean estimate of the projected feature items and corresponding feature items of thereference 3D representation are generated. The rigid motion may be constrained by known 3D position information associated with the source 2D projection(s). - In some embodiments, the feature items may include curves as well as points which are extracted from the source projection using dynamic programming. Further, areas as well as surfaces and or subvolumes may be used as features generated via isocontouring (such as via the Marching Cubes algorithm) or automated segmentation algorithms. The feature items used in the matching process may be found automatically by using correspondences between the 2D source projection(s) and projected imagery of at least one
reference 3D object. - The invention may further comprise the step of creating a 3D representation of the source 2D projection(s) by deforming the located (i.e., best-fitting)
reference 3D representation so as to resemble the source multifeatured object. In one embodiment, the deformation is a large deformation diffeomorphism, which serves to preserve the geometry and topology of thereference 3D representation. The deformation step may deform the located 3D representation so that feature items in the source 2D projection(s) align with corresponding features in the locatedreference 3D representation. The deformation step may occur with or without rigid motions and may include affine motions. Further, the deformation step may be constrained by at least one of known 3D position information associated with the source 2D projection(s), and 3D data of the source object. The deformation may be performed using a closed form expression. - In a second aspect, the invention comprises a system for comparing at least one source 2D projection of a source multifeatured object to a reference library of 3D reference objects. The system comprises a database comprising a plurality of
reference 3D representations of generically similar multifeatured objects and an analyzer for performing a viewpoint-invariant search of thereference 3D representations to locate thereference 3D representation having a 2D projection most resembling the source projection(s). In some embodiments, the analyzer determines resemblance by a degree of alignment between feature items in the 3D representation and corresponding feature items in the source 2D projection(s). The analyzer may search eachreference 3D representation over a range of possible 2D projections of the 3D representation without actually generating any projections. In some embodiments, the analyzer searches over a range of possible 2D projections by computing a rigid motion of thereference 3D representation optimally consistent with a viewpoint of the source multifeatured object in at least one of the 2D projections. The rigid motions may comprise pitch, roll, yaw, and translation in three dimensions. The analyzer may be configured to perform automatic camera calibration by estimating camera parameters. such as aspect ratio and field of view, from image landmarks. - In some embodiments, the analyzer is configured to determine the optimum rigid motion by estimating a conditional mean of feature items comprising points, curves, surfaces, and subvolumes in a 3D coordinate space associated with the
reference 3D representation such that the feature items are projectionally consistent with feature items in the source 2D projection(s). The analyzer is further configured to generate MMSE estimates between the conditional mean estimate of the projected feature items and corresponding feature items of thereference 3D representation. The rigid motion may be constrained by known 3D position information associated with the source 2D projection(s). - In some embodiments, the analyzer is configured to extract feature items from the source projection using dynamic programming. In further embodiments, the analyzer may be configured to find feature items used in the matching process automatically by using correspondences between source imagery and projected imagery of at least one
reference 3D object. - The invention may further comprise a deformation module for creating a 3D representation of the at least one source 2D projection by deforming the located (i.e., best-fitting)
reference 3D representation so as to resemble the source multifeatured object. In one embodiment, the deformation module deforms the locatedreference 3D representation using large deformation diffeomorphism, which serves to preserve the geometry and topology of thereference 3D representation. The deformation module may deform the located 3D representation so that feature items in the source 2D projection(s) align with corresponding features in the locatedreference 3D representation. The deformation module may or may not use rigid motions and may use affine motions. Further, the deformation module may be constrained by at least one of known 3D position information associated with the source 2D projection(s) and 3D data of the source object. The deformation module may operate in accordance with a closed form expression. - In a third aspect, the invention comprises a method of comparing a
source 3D object to at least onereference 3D object. The method involves creating 2D representations of the source object and the reference object(s) and using projective geometry to characterize a correspondence between thesource 3D object and areference 3D object. For example, the correspondence may be characterized by a particular viewpoint for the 2D representation of the 3D source object. - In a fourth aspect, the invention comprises a system for comparing a
source 3D object to at least onereference 3D object. The system comprises a projection module for creating 2D representations of the source object and the reference object(s) and an analyzer which uses projective geometry to characterize a correspondence between thesource 3D object and areference 3D object. - In a fifth aspect, the above described methods and systems are used for the case when the 3D object is a face and the
reference 3D representations are avatars. - In a sixth aspect, the invention comprises a method for creating a 3D representation from at least one source 2D projection of a source multifeatured object. In accordance with the method, at least one
reference 3D representation of a generically similar object is provided, one of the provided representation(s) is located, and a 3D representation of the source 2D projection(s) is created by deforming the located reference representation in accordance with the source 2D projection(s) so as to resemble the source multifeatured object. In some embodiments, the source 2D projection(s) is used to locate the reference representation. In further embodiments, the set of reference representations includes more than one member, and the reference most resembling the source 2D projection(s) is located by performing a viewpoint-invariant search of the set of reference representations, without necessarily actually generating any projections. The search may include computing a rigid motion of the reference representation optimally consistent with a viewpoint of the source multifeatured object in at least one of the source projections. - In a preferred embodiment, a 3D representation of the source projection(s) is created by deforming the located reference representation so as to resemble the source multifeatured object. The deformation may be a large deformation diffeomorphism. In some embodiments, the deformation deforms the located reference so that feature items in the source projection(s) align with corresponding feature items in the located 3D reference representation. In some embodiments, the deformation is performed in real time.
- In a seventh aspect. the invention comprises a system for creating a 3D representation from at least one source 2D projection of a source multifeatured object. The system includes a database of at least one
reference 3D representation of a generically similar object, and an analyzer for locating one of the provided representation(s). The system further includes a deformation module for creating a 3D representation of the source 2D projection(s) by deforming the located reference representation in accordance with the source 2D projection(s) so as to resemble the source multifeatured object. In some embodiments, the analyzer uses the source 2D projection(s) to locate the reference representation. In further embodiments, the set of reference representations includes more than one member, and the analyzer locates the reference most resembling the source 2D projection(s) by performing a viewpoint-invariant search of the set of reference representations, without necessarily actually generating any projections. The search may include computing a rigid motion of the reference representation optimally consistent with a viewpoint of the source multi featured object in at least one of the source projections. - In a preferred embodiment, the deformation module creates a 3D representation of the source projection(s) by deforming the located reference representation so as to resemble the source multifeatured object. The deformation may be a large deformation diffeomorphism. In some embodiments, the deformation module deforms the located reference so that feature items in the source projection(s) align with corresponding feature items in the located 3D reference representation. In some embodiments, the deformation module operates in real time.
- In the drawings, like reference characters generally refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the invention. In the following description, various embodiments of the invention are described with reference to the following drawings, in which:
-
FIG. 1 schematically illustrates the various components of the invention, starting with the target object, the reference objects, and yielding an optimal 3D model after performing a search and deformation. -
FIGS. 2A , 2B, and 2C schematically illustrate the components of a 3D avatar. -
FIG. 3 schematically illustrates the matching of feature items in the 2D imagery. -
FIG. 4 is a block diagram showing a representative hardware environment for the present invention. -
FIG. 5 is a block diagram showing components of the analyzer illustrated inFIG. 4 . -
FIG. 6 is a block diagram showing the key functions performed by the analyzer. -
FIG. 1 illustrates the basic operation of the invention in the case where the 3D target multifeatured object is a face and the set ofreference 3D representations are avatars. The matching process starts with a set ofreference 3D avatars which represent, to the extent practicable, the range of different types of heads to be matched. For example, the avatars may include faces of men and women, faces with varying quantities and types of hair, faces of different ages, and faces representing different races. Typically the reference set includes numerous (e.g., several hundred or more) avatars, though the invention works with as few as one reference object, and as many for which storage space and compute time are available. In some situations, only a single reference avatar will be used. This case may arise, for example, when the best-fitting avatar has been selected manually, or by some other means, or when only one reference avatar is available. InFIG. 1 , the source data of the target face is illustrated as a single 2D photograph of thetarget 3D face taken from an unknown viewpoint. First, selected features to be used for matching are identified in the source photograph. The features may be points, such as the extremities of the mouth and eyes, or curves representing a profile, an eyebrow, or other distinctive curve, or subareas such as an eyebrow, nose or cheek. The corresponding features are identified in the reference avatars. The selection of features in the target photograph, and the identification of corresponding features in the reference avatars may be done automatically according to the invention. Next, a viewpoint-invariant search is conducted in which each 3D avatar is notionally subjected to all possible rigid motions and the features projected into 2D. The positions of the projected avatar features are compared to the feature positions in the target photograph. The avatar for which a particular rigid motion provides the closest fit between projected features and those of the source photograph is selected as the best reference avatar.FIG. 1 illustrates the best-fitting reference avatar to be the middle one. - Next, the best reference avatar is deformed to match the target photograph more closely. First the features of the photograph are reverse projected to the coordinates of the best reference avatar in the orientation and position corresponding to the best match. The mesh points of the avatar are then deformed in 3D to minimize the distances between the reverse-projected features of the photograph and the corresponding avatar features. The avatar resulting from this deformation will be a closer approximation to the
target 3D face. The rigid motion search and deformation steps may be repeated iteratively, e.g., until the quality of fit no longer improves appreciably. The resulting 3D model is the optimal match to the target face. - The invention can be used effectively even when the source imagery includes only a part of the target face, or when the target face is partially obscured, such as, for example, by sunglasses or facial hair. The approach of the invention is suitable for any multifeatured object, such as faces, animals, plants, or buildings. For ease of explanation, however, the ensuing description will focus on faces as an exemplary (and non-limiting) application.
-
FIGS. 2A , 2B, and 2C show the components of a representative avatar. In one embodiment of the invention, the geometry of the avatar is represented by a mesh of points in 3D which are the vertices of set of triangular polygons approximating the surface of the avatar.FIG. 2A illustrates a head-onview 202 and aside view 204 of the triangular polygon representation. In one representation, each vertex is given a color value, and each triangular face may be colored according to an average of the color values assigned to its vertices. The color values are determined from a2D texture map 206, illustrated inFIG. 2B , which may be derived from a photograph. InFIG. 2C , the final avatar with texture is illustrated in a head-onview 208 andside view 210. The avatar is associated with a coordinate system which is fixed to it, and is indexed by three angular degrees of freedom (pitch, roll, and yaw), and three translational degrees of freedom of the rigid body center in three-space. In addition, individual features of the avatar, such as the chin, teeth and eyes may have their own local coordinates (e.g., chin axis) which form part of the avatar description. The present invention may be equally applied to avatars for which a different data representation is used. For example, texture values may be represented as RGB values, or using other color representations, such as HSL. The data representing the avatar vertices and the relationships among the vertices may vary. For example, the mesh points may be connected to form non-triangular polygons representing the avatar surface. - The invention may include a conventional rendering engine for generating 2D imagery from a 3D avatar. The rendering engine may be implemented in OpenGL, or in any other 3D rendering system, and allows for the rapid projection of a 3D avatar into a 2D image plane representing a camera view of the 3D avatar. The rendering engine may also include the specification of the avatar lighting, allowing for the generation of 2D projections corresponding to varying illumination of the avatar. Lighting corresponding to a varying number of light sources of varying colors, intensities, and positions may be generated.
- The feature items in the 2D source projection which are used for matching are selected by hand or via automated methods. These items may be points or curves. When the source projection includes a front view, suitable points may be inflection points at the lips, points on the eyebrows, points at the extremities of the eyes, or extremities of nostrils, and suitable curves may include an eyebrow or lip. When the source projection includes a side view, the feature points corresponding to the profile are used and may include the tip of the nose or chin. Suitable feature item curves may include distinct parts of the profile, such as nose, forehead, or chin.
- When the feature items are determined manually, a user interface is provided which allows the user to identify feature points individually or to mark groups of points delineated by a spline curve, or to select a set of points forming a line.
- The automated detection of feature items on the 2D source projection is performed by searching for specific features of a face, such as eyeballs, nostrils, and lips. As understood by those of ordinary skill in the art, the approach may use Bayesian classifiers and decision trees in which hierarchical detection probes are built from training data generated from actual avatars. The detection probes are desirably stored at multiple pixel scales so that the specific parameters, such as for orientation of a feature, are only computing on finer scales if the larger-scale probes yield a positive detection. The feature detection probes may be generated from image databases representing large numbers of individuals who have had their features demarcated and segregated so that the detection probes become specifically tuned to these features. The automated feature detection approach may use pattern classification, Bayes nets, neural networks, or other known techniques for determining the location of features in facial images.
- The automated detection of curve features in the source projection may use dynamic programming approaches to generate curves from a series of points so as to reduce the amount of computation required to identify an optimal curve and maximize a sequentially additive cost function. Such a cost function represents a sequence of features such as the contrast of the profile against background, or the darkness of an eyebrow, or the crease between lips. A path of N points can be thought of as consisting of a starting node x0 and a set of vectors v0, v1, . . . , vN−1 connecting neighboring nodes. The nodes comprising this path are defined as
-
- Rather than searching over all paths of length N, dynamic programming may be used to generate maximum (or minimum) cost paths. This reduces the complexity of the algorithm from KN to NK2 where N is the length of a path and K is the total number of nodes, as dynamic programming takes advantage of the fact that the cost is sequentially additive, allowing a host of sub-optimal paths to be ignored. Dynamic programming techniques and systems are well-characterized in the art and can be applied as discussed herein without undue experimentation.
- Next, the 3D rotation and translation from the avatar coordinates to the source projection is determined. This corresponds to finding the viewpoint from which the source projection was captured. In preferred embodiments, this is achieved by calculating the position of the avatar in 3D space that best matches the set of selected feature items in the 2D source projection. Generally, these feature items will be points, curves, or subareas and the source projection will be a photograph on which the position of these items can be measured, either manually or automatically. The position calculation may be based on the computation of the conditional mean estimate of the reverse projection positions in 3D of the 2D feature items, followed by the computation of MMSE estimates for the rotation and translation parameters in 3D, given the estimates of the 3D positions of the feature items. Since position in 3D space is a vector parameter, the MMSE estimate for translation position is closed form; when substituted back into the squared error function, it gives an explicit function in terms of only the rotations. Since the rotations are not vector parameters, they may be calculated using non-linear gradient descent through the tangent space of the group or via local representation using the angular velocities of the skew-symmetric matrices.
- In addition to or in lieu of the least squares or weighted least squares techniques described herein, the distance metrics used to measure the quality of fit between the reverse projections of feature items from the source imagery and corresponding items in the 3D avatar may be, for example, Poisson or other distance metrics which may or may not satisfy the triangle inequality.
- If feature items measured in 3D are available, such as from actual 3D source data from 3D cameras or scanners. the feature item matching may be performed directly, without the intermediate step of calculating the conditional mean estimate of the deprojected 2D features. The cost function used for positioning the 3D avatar can be minimized using algorithms such as closed form quadratic optimization, iterative Newton descent or gradient methods.
- The 3D positioning technique is first considered without deformation of the reference avatar. In the following, a 3D reference avatar is referred to as a CAD (computer-aided design) model, or by the symbol CAD. The set of xj=(xj, yj, zj), j=1, . . . , N features is defined on the CAD model. The projective geometry mapping is defined as either positive or negative z, i.e., projection occurs along the z axis. In all the projective geometry
-
- (for negative z-axis projection), or
-
-
- where n is the cotangent of the projective angle. The following data structures are defined throughout:
-
- with (•)′ matrix transpose, and the identity matrix
-
- For negative (i.e., z<0) mapping
-
- and the change
-
- is made.
- The basis vectors, Z1,Z2,Z3 at the tangent to the 3×3 rotation element O are defined as:
-
Z 1=11Oold =[o 21 , o 22 , o 23 , −o 11 , −o 12 , −o 13, 0, 0, 0]′ (Equation 3) -
Z 2=12 O old =[o 31 , o 32 , o 33, 0, 0, 0, −o 11 , −o 12 , −o 13]′ (Equation 4) -
Z 3=13 O old=[0, 0, 0, o 31 , o 32 , o 33 , −o 21 , −o 22 , −o 23]′ (Equation 5) -
- The reverse projection of feature points from the 2D projection may now be performed. Given the feature points pj=(pj1, pj2), j=1, 2, . . . in the image plane, the minimum norm-estimates for {circumflex over (z)}i are given by, Ô, {circumflex over (b)} as
-
- and the MMSE, Ô, {circumflex over (b)} satisfies
-
- During the process of matching a source image to reference avatars, there may be uncertainty in the determined points x, implying that cost matching is performed with a covariance variability structure built in to the formula. In this case, the norm has within it a 3×3 matrix which represents this variability in the norm.
-
-
-
- The optimum translation rotation solutions are preferably generated as follows. Compute the 3×9 matrix Mt=Xi −
Q −1 XQ and evaluate exhaustively the cost function choosing minimum Ô and computing the translation -
- with minimum Ô attained, for example, via brute force search over the orthogonal group which may for example be parameterized by pitch, roll or yaw or running the gradient search algorithm to convergence as follows.
-
- In a typical application some information about the position of the object in 3D space is known. For example, in a system which takes a succession of photographs of a moving source object, such as in a tracking system, the position from a previous image may be available. The invention may incorporate this information into the matching process as follows. Given a sequence of points pi, i=1, . . . , N and a rigid transformation of the form A=O, b: xOx+b (centered around xe=0), the MMSE of rotation and translation Ô, {circumflex over (b)} satisfies:
-
- The 3×9 matrix Mi and a 3×1 column vector N are computed:
-
M i X i −Q Σ −1 X Q , N=Q Σ −1 X QQ Σ,=(Q +Σ −1), ψ=Q Σ −1Σu , φ=Q Σ −1Σμ−μ, Σμ=Σ−1μ. (Equation 12) - The translation is then determined {circumflex over (b)}=−
Q Σ −1XQÔ+Q Σ −1Σμ at the minimum Ô obtained by exhaustive search or gradient algorithm run until convergence: -
- with the projection onto the basis vectors Z1,Z2,Z3 of equations 3-5 defined at the tangent to Oold in the exponential representation where αnew are the directional derivatives of cost.
- The rotation/translation data may be indexed in many different ways. For example, to index according to the rotation around the center of the object, rather than fixed external world coordinates, the coordinates are just reparameterized by defining a {tilde over (x)}←x−xc. All of the techniques described herein remain the same.
- The preferred 3D algorithm for rigid motion efficiently changes states of geometric pose for comparison to the measured imagery. The preferred 3D algorithm for diffeomorphic transformation of geometry matches the geometry to target 2D image features. It should be understood, however, that other methods of performing the comparison of the 3D representation to the source imagery may be used, including those that do not make use of specific image features.
- Once the rigid motion (i.e., rotation and translation) that results in the best fit between 2D source imagery and a selected 3D avatar is determined, the 3D avatar may be deformed in order to improve its correspondence with the source imagery. The allowed deformations are generally limited to diffeomorphisms of the original avatar. This serves to preserve the avatar topology, guaranteeing that the result of the deformation will be a face. The deformations may also enforce topological constraints, such as the symmetry of the geometry. This constraint is especially useful in situations where parts of the source object are obscured, and the full geometry is inferred from partial source information.
-
FIGS. 3A and 3B illustrate the effect of avatar deformation on the matching of the avatar to the source imagery. InFIG. 3A , feature points are shown as black crosses on thesource image 302. An example is the feature point at the left extremity of theleft eyebrow 304. The projections of the corresponding feature points belonging to the best-matching reference avatar with optimal rigid motion prior to deformation are shown as white crosses. It can be seen that the projected point corresponding to the left extremity of theleft eyebrow 306 is noticeably displaced from itscounterpart 304. InFIG. 3B , thesame source image 302 is shown with feature points again indicated by black crosses. This time, the best-fitting avatar feature points shown as white crosses are now projected after deformation. The correspondence between source feature points and avatar feature points is markedly improved, as shown, for example, by the improved proximity of the projected lefteyebrow feature point 308 to itssource counterpart 304. - The 3D avatar diffeomorphism calculation starts with the initial conditions for placement of the avatar determined by the feature item detection and computation of the best-fitting rigid motion and the original geometry of the avatar. It then proceeds by allowing all of the points on the avatar to move independently according to a predefined formula to minimize the distance between the deformed avatar points in 3D and the conditional mean estimates of the 2D landmark points reverse projected to the 3D coordinates. Once this diffeornorphism is calculated, the 3D landmark rigid motion algorithm is applied again to the source projections and feature items to find the best guess of the camera positions given this newly transformed avatar with its new vertex positions. Subsequently, a new diffeomorphism is generated, and this process is continued until it converges. Alternatively, iteration may not be used, with the rigid motion calculation being performed only a single time, and just one diffeomorphism transformation applied. In the case where camera orientations (i.e., the viewpoint of the measured source projections) are known precisely, these can be used as fixed inputs to the calculation, with no rigid transformation required. When the measured sets of feature items are in 3D, such as from a cyber scan or 3D camera observations of the candidate head, the avatar transformed onto the candidate sets of points without any intermediate generation of the candidate points in 3D space via the conditional mean algorithm for generating 3D points from 2D sets of points.
- The diffeomorphic deformation of an avatar proceeds as follows. Given the set xj=(xj, yj, zj), j=1, . . . , N feature items defined on the CAD model, with the projective geometry mapping with
-
- where n is cotangent of the angle, and w,h are aspect ratio widths and heights,
-
- with observations of the feature items through the projective geometry
-
- The goal is to construct the deformation of the CAD model x→x+u(x), x ∈ CAD with unknown camera rigid motions corresponding to the measured projective image feature items. The projective points for each orientation v=1, . . . , V, and smoothing matrices
-
- are constructed, where for example Kij=diag (e−a∥x
i −xj ∥, e−a∥xj −xj ∥, e−a∥xj −xj ∥) corresponds to the square root inverse Laplacian operator L=diag (−∇2+c). - In one embodiment, the avatar may be deformed with small deformations only and no rigid motions. For this embodiment, it is assumed that the measured feature items are all points from a single camera viewing which generated the projected source image in which the feature points were measured. The goal is to construct the deformation of the CAD model constructing the mapping x→x+u(x), x ∈ CAD:
-
- First, the transformation of the model x→x+u(x) with u(x)=Σn−1 NK(xn, x)βn and where
-
- is computed. Next, rigid motions are added and the following equation solved for the optimizer:
-
- The transformation of the model using small deformation x→x+u(x) is computed, where u(x)=Σn=1 NK(xn, x)βn and
-
- In another embodiment, diffeomorphic deformations with no rigid motions of the avatar are applied. In the case that the change in shape of the face is extensive the large deformation φ: xφ(x) satisfying φ=φ1φt=∫oVs(φs(x))ds+x,x ∈ CAD is generated. The deformation of the CAD model constructing the mapping xφ(x), x ∈ CAD is constructed:
-
- Using the initialization vnew=0,φnew(x)=x, x ∈ CAD, mappings are repeatedly generated from the new vector field by running an iterative algorithm until convergence:
-
- where
-
-
- Using the initialization vnew=0,φnew(x)=x, x ∈ CAD, a mapping is generated from the new vector field by running an iterative algorithm until convergence:
-
- In a further embodiment, the deformation may be performed in real time for the case when the rigid motions (i.e., the rotation/translation) which bring the avatar into correspondence with the one or more source 2D projection are not known. A similar approach to the one above is used, with the addition of an estimation of the rigid motions using the techniques described herein. The initialization unew=0 is used. Rigid motions are calculated using the rotation/translation techniques above to register the CAD model xx+unew(x) to each photograph, generating rigid motions O(v)new,b(v)new,v=1, 2, . . . O(v)new,b(v)new are fixed from the previous step, and the deformation of the CAD model xx+unew(x) or large deformation xφ(x) are computed using the above techniques to solve the real-time small deformation or large deformation problem:
-
- In another embodiment, the avatar is deformed in real-time using diffeomorphic deformations. The solution to the real-time deformation algorithm generates a deformation which may be used as an initial condition for the solution of the diffeomorphic deformation. Real-time diffeomorphic deformation is accomplished by incorporating the real-time deformations solution as an initial condition and then performing a small number (in the region of 1 to 10) iterations of the diffeomorphic deformation calculation.
- The deformation may include affine motions. For the affine motion A: x→Ax where A is the 3×3 generalized linear matrix so that
-
- the least squares estimator Â: x→Âx is computed:
-
- In many cases, both feature items in the projective imagery as well as the imagery itself can be used to drive the deformation of the avatar. Augmentation of source data to incorporate source imagery may improve the quality of the fit between the deformed avatar and the target face. To implement this, one more term is added to the deformation techniques. Let I be the measured imagery, which in general includes multiple measured images I(v),v=1, 2, . . . corresponding to an indexed sequence of pixels indexed by p ∈ [0,1]2, with the projection mapping points
-
- For the discrete setting of pixels in the source image plane with color (R,G,B) template, the observed projective Π(p) is an (R,G,B) vector and the projective matrix becomes
-
- operating on points (x,y,z) ∈ IR3 according to the projective matrix
-
- the point x(p) being the revealed point which is not occluded (closest point to the projection on the ray) on the 3D CAD model which projects to the point p in the image plane. Next, the projected template matrices resulting from finite differences on the (R,G,B) components at the projective coordinate p of the template value are required. The norm is interpreted componentwise:
-
- with matrix norm ∥A−B∥2=|Ar−Br|2+|Ag−Bg|2+|Ab−Bb|2.
- Associated with each image is a translation/rotation assumed already known from the previous rigid motion calculation techniques. The following assumes there is one 2D image, with O,b identity, and let any of the movements be represented as x→x+u(x). Then u(x)=Ox−x is a rotational motion, u(x)=b is a constant velocity, u(x)=ΣieiEi(x) is a constrained motion to a basis function such as “chin rotation,” “eyebrow lift,” etc., and the general motion u is given by:
-
- This is linear in u so closed-form expressions exist for each of the forms of u, for example, for the unconstrained general spline motion,
-
û(x(p))=({tilde over (∇)}Π(p){tilde over (∇)}tΠ(p))−1 İ(p){tilde over (∇)}Π(p). (Equation 36) - This approach can be incorporated into the other embodiments of the present invention for the various possible deformations described herein.
- In the situation where large numbers of feature points, curves, and subvolumes are to be automatically generated from the source projection(s) and 3D data (if any), image matching is performed directly on the source imagery or on the fundamental 3D volumes into which the source object can be divided. For the case where the avatar is generated from 2D projective photographic images, the measured target projective image has labeled points, curves, and subregions generated by diffeomorphic image matching. Defining a template projective exemplar face with all of the labeled submanifolds from the avatar, the projective exemplar can be transformed bijectively via the diffeomorphisms onto the target candidate photograph, thereby automatically labeling the target photographs into its constituent submanifolds. Given these submanifolds, the avatars can then be matched or transformed into the labeled photographs. Accordingly, in the image plane a deformation φ: xφ(x) satisfying φ=∫0 1vt(φt(x))dt+x, x ∈ R2 is generated. The template and target images I0, I1 are transformed to satisfy
-
- The given diffeomorphism is applied to labeled points, curves, and areas in the template I0 thereby labeling those points, curves, and areas in the target photograph.
- When the target source data are in 3D, the diffeomorphisms are used to define bijective correspondence in the 3D background space, and the matching is performed in the volume rather than in the image plane.
- The following techniques may be used to select avatar models automatically. Given a collection of avatar models {CADa,a=1, 2, . . . }, and a set of measured photographs of the face of one individual, the task is to select the avatar model which is most representative of the individual face being analyzed. Let the avatar models be specified via points, curves, surfaces, or subvolumes. Assume for example N feature initial and target points, xn a,xn ∈ IRd,n=1, . . . , N, with xn=xn a+u(xn a), one for each avatar a=1, 2, . . . .
- In one embodiment, the avatar is deformed with small deformations only and no rigid motions. For this embodiment, it is assumed that the measured feature items are all points from a single camera viewing which generated the projected source image in which the feature points were measured. The matching xn a xn a+u(xn a), n=1, . . . , N is constructed and the CADa model which is of smallest metric distance is selected. The optimum selected avatar model is the one closest to the candidate in the metric. Any of a variety of distance functions may be used in the selection of the avatar, including the large deformation metric from the diffeomorphism mapping technique described above, the real-time metric described above. the Euclidean metric, and the similitude metric of Kendall. The technique is described herein using the real-time metric. When there is no rigid motion, then the CAD model is selected to minimize the metric based on one or several sets of features from photographs, here described for one photo:
-
- In other embodiments both metrics including unknown or known rigid motions, large deformation metrics, or affine motions can be used such as described in equations 28 and 29, respectively.
- For selecting avatars given 3D information such as features of points, curves, surfaces and or subvolumes in the 3D volume, then the metric is selected which minimizes the distance between the measurements and the family of candidate CAD models. First, the K matrix defining the quadratic form metric measuring the distance is computed:
-
-
- The minimum none is determined by the error between the CAD model feature points and the photographic feature points.
- The present invention may also be used to match to articulated target objects. The diffeomorphism and real-time mapping techniques carry the
template 3D representations bijectively onto the target models. carrying all of the information in the template. The template models are labeled with different regions corresponding to different components of the articulated object. For example, in the case of a face, the articulated regions may include teeth, eyebrows, eyelids, eyes, and jaw. Each of these subcomponents can be articulated during motion of the model according to an articulation model specifying allowed modes of articulation. The mapping techniques carry these triangulated subcomponents onto the targets, thereby labeling them with their subcomponents automatically. The resulting selected CAD model therefore has its constituent parts automatically labeled, thereby allowing each avatar to be articulated during motion sequences. - In the case when direct 3D measurement of the source object is available xnyn ∈ 3, n=1, . . . , N from points, curves, surfaces, or subvolumes, the techniques for determining the rotation/translation correspondences are unchanged. However, since the matching terms involve direct measurements in the volume, there is no need for the intermediate step to determine the dependence on the unknown z-depth via the MMSE technique.
- Accordingly, the best matching rigid motion corresponds to:
-
- The real-time deformation corresponds to:
-
- The diffeomorphism deformation corresponds to with
-
- The techniques described herein also allow for the automated calibration camera parameters, such as the aspect ratio and field of view. The set of xj=(xj,yj,zj), j=1, . . . , N features are defined on the CAD model. The positive depth projective geometry mapping with
-
- is defined, according to
-
- Given are observations of some features through the projective geometry
-
- The calibration of the camera is determined under the assumption that there is no transformation (affine or other) of the avatar. The z value is parameterized by incorporating the n frustrum distance so that all depth coordinates are the above coordinates plus frustrum depth. Videos can show different aspect ratios
-
- and fields-of-view
-
- The technique estimates the aspect ratios γ1,γ2 from measured points Pi(γ1Pi1,γ2Pi2, 1)t, i=1, . . . N:
-
- Using the initialization γ1 new=γ2 new=1, the calculation is run to convergence.
- In the first step, the data terms
-
- are solved, and the following rotations/translations are computed:
-
- Next, the expression
-
- is maximized using an optimization method, such as Newton Raphson, gradient or conjugate gradient. Using the gradient algorithm, for example, the calculation is run to convergence, and the first step is repeated. The gradient method is shown here, with step-size selected for stability:
-
- The techniques described herein may be used to compare a
source 3D object to a single reference object. 2D representations of the source object and the reference object are created, and the correspondence between them is characterized using mathematical optimization and projective geometry. Typically, the correspondence is characterized by specifying the viewpoint from which the 2D source projection was captured. - Refer now to
FIG. 4 , which illustrates ahardware system 400 incorporating the invention. As indicated therein, the system includes a video source 402 (e.g., a video camera or a scanning device) which supplies a still input image to be analyzed. The output of thevideo source 402 is digitized as a frame into an array of pixels by adigitizer 404. The digitized images are transmitted along thesystem bus 406 over which all system components communicate, and may be stored in a mass storage device (such as a hard disc or optical storage unit) 408 as well as in main system memory 410 (specifically, within a partition defining a series of identically sized input image buffers) 412. - The operation of the illustrated system is directed by a central-processing unit (“CPU”) 414. To facilitate rapid execution of the image-processing operations hereinafter described, the system preferably contains a graphics or image-
processing board 416; this is a standard component well-known to those skilled in the art. - The user interacts with the system using a
keyboard 418 and a position-sensing device (e.g., a mouse) 420. The output of either device can be used to designate information or select particular points or areas of ascreen display 420 to direct functions performed by the system. - The
main memory 410 contains a group of modules that control the operation of theCPU 414 and its interaction with the other hardware components. Anoperating system 424 directs the execution of low-level, basic system functions such as memory allocation, file management and operation ofmass storage devices 408. At a higher level, theanalyzer 426, implemented as a series of stored instructions, directs execution of the primary functions performed by the invention, as discussed below: and instructions defining auser interface 428 allow straightforward interaction overscreen display 422. Theuser interface 428 generates words or graphical images on thedisplay 422 to prompt action by the user, and accepts commands from thekeyboard 418 and/or position-sensingdevice 420. Finally, thememory 410 includes apartition 430 for storing for storing a database of 3D reference avatars, as described above. - The contents of each
image buffer 412 define a “raster,” i.e., a regular 2D pattern of discrete pixel positions that collectively represent an image and may be used to drive (e.g., by means of image-processing board 416 or an image server)screen display 422 to display that image. The content of each memory location in a frame buffer directly governs the appearance of a corresponding pixel on thedisplay 422. - It must be understood that although the modules of
main memory 410 have been described separately, this is for clarity of presentation only; so long as the system performs all the necessary functions, it is immaterial how they are distributed within the system and the programming architecture thereof Likewise, though conceptually organized as grids, pixelmaps need not actually be stored digitally in this fashion. Rather, for convenience of memory utilization and transmission, the raster pattern is usually encoded as an ordered array of pixels. - As noted above, execution of the key tasks associated with the present invention is directed by the
analyzer 426, which governs the operation of theCPU 414 and controls its interaction withmain memory 410 in performing the steps necessary to match and deformreference 3D representations to match a target multifeatured object.FIG. 5 illustrates the components of a preferred implementation of theanalyzer 426. Theprojection module 502 takes a 3D model and makes a 2D projection of it onto any chosen plane. In general, anefficient projection module 502 will be required in order to create numerous projections over the space of rotations and translations for each of the candidate reference avatars. Thedeformation module 504 performs one or more types of deformation on an avatar in order to make it more closely resemble the source object. The deformation is performed in 3D space, with every point defining the avatar mesh being free to move in order to optimize the fit to the conditional mean estimates of the reverse projected feature items from the source imagery. In general. deformation is only applied to the best-fitting reference object, if more than one reference object is supplied. Therendering module 506 allows for the rapid projection of a 3D avatar into 2D with the option of including the specification of the avatar lighting. The 2D projection corresponds to the chosen lighting of the 3D avatar. Thefeature detection module 508 searches for specific feature items in the 2D source projection. The features may include eyes, nostrils, lips, and may incorporate probes that operate at several different pixel scales. -
FIG. 6 illustrates the functions of the invention performed in main memory. Instep 602, the system examines the source imagery and automatically detects features of a face. such as eyeballs, nostrils, and lips that can be used for matching purposes, as described above. Instep 604, the detected feature items are reverse projected into the coordinate frame of the candidate avatar, as described above and using equation 7. Instep 606, the optimum rotation/translation of the candidate avatar is estimated using the techniques described above and using equations 8, 9 and 10. Instep 608, any prior information that may be available about the position of the source object with respect to the available 2D projections is added into the computation, as described herein using equations 1 1-13. When 3D measurements of the source are available, this data is used to constrain the rigid motion search as shown instep 610 and as described above with reference to equations 41-43. When the rotation/translation search 606 is completed over all thereference 3D avatars, the best-fitting avatar is selected instep 612, as described above, with reference to equations 38-40. Subsequently, the best-fitting avatar located instep 612 is deformed instep 614. 3D measurements of thesource object 610, if any, are used to constrain thedeformation 614. In addition, portions of thesource imagery 616 itself may be used to influence thedeformation 614. - The invention provides for several different kinds of deformation which may be optionally applied to the best-fitting reference avatar in order to improve its correspondence with the target object. The deformations may include real-time deformation without rigid motions in which a closed form expression is found for the deformation, as described above using equations 18, 19. A diffeomorphic deformation of the avatar with no rigid motions may be applied (equations 22-24). Alternatively, a real time deformation with unknown rigid motion of the avatar may be deployed (equations 28, 29). A real-time diffeormorphic deformation may be applied to the avatar by iterating the real-time deformation. The avatar may be deformed using affine motions (equations 30, 31). The deformation of the avatar may be guided by matching a projection to large numbers of feature items in the source data, including the identification of submanifolds within the avatar, as described above with reference to equation 37. When the target object is described by an articulated model, the deformations described above may be applied to each articulated component separately.
- The invention enables camera parameters, such as aspect ratio and field of view to be estimated as shown in
step 618 and described above. with reference to equations 44-49. - As noted previously, while certain aspects of the hardware implementation have been described for the case where the target object is a face and the reference object is an avatar, the invention is not limited to the matching of faces, but may be used for matching any multifeatured object using a database of
reference 3D representations that correspond to the generic type of the target object to be matched. - It will therefore be seen that the foregoing represents a highly extensible and advantageous approach to the generation of 3D models of a target multifeatured object when only partial information describing the object is available. The terms and expressions employed herein are used as terms of description and not of limitation, and there is no intention, in the use of such terms and expressions, of excluding any equivalents of the features shown and described or portions thereof, but it is recognized that various modifications are possible within the scope of the invention claimed. For example, the various modules of the invention can be implemented on a general-purpose computer using appropriate software instructions, or as hardware circuits, or as mixed hardware-software combinations (wherein, for example, pixel manipulation and rendering is performed by dedicated hardware components).
Claims (8)
1-76. (canceled)
77. A method involving at least one source 2D image of a source 3D object, the method comprising:
providing a reference 3D representation; and
simultaneously searching over rigid motions and deformations of the reference 3D representation to identify a best-match reference 3D representation most resembling the at least one source 2D projection,
wherein simultaneously searching comprises searching over rigid motions of the reference 3D representation and for each orientation of the reference 3D representation in the search over rigid motions of the reference 3D representation, using a closed form expression to compute a deformed reference 3D representation that generates a best-fit with the at least one source 2D image, and
wherein the best-match 3D representation is the deformed reference 3D representation for the orientation in the search that yields a best best-fit.
78. The method of claim 77 , wherein the closed form expression corresponds to a back-projection into 3D space of the at least one source 2D image.
79. The method of claim 1, wherein the closed form expression corresponds to de-projected positions in 3D space of feature items from the at least one source 2D image.
80. The method of claim 1, wherein simultaneously searching over rigid motions and deformations of the reference 3D representation to identify the best-match reference 3D representation most resembling the at least one source 2D projection is performed without generating any 2D projections of the reference 3D representation or deformed versions thereof.
81. A method involving at least one source 2D image of a source 3D object, the method comprising:
providing a reference 3D representation; and
searching over rigid motions and deformations of the reference 3D representation to identify a best match reference 3D representation most resembling the at least one source 2D projection,
wherein said searching involves applying both rigid motion and deformation operators to that reference 3D representation to generate multiple versions of the reference 3D representation, and for each version of the reference 3D representation, computing a measure of fit between that version of the reference 3D representation and the at least one source 2D image,
wherein the best-fit 3D representation is the version of the reference 3D representation that yields a best measure of fit, and
wherein the deformation operators are numerical representations of transformations that are of infinite dimension.
82. The method of claim 1, wherein searching over rigid motions and deformations of the reference 3D representation to identify a best match reference 3D representation most resembling the at least one source 2D projection is performed without actually generating any projections.
83. A method involving at least one source 2D image of a source 3D object, the method comprising:
providing a reference 3D representation; and
searching over rigid motions and deformations of the reference 3D representation to identify a best match reference 3D representation most resembling the at least one source 2D projection,
wherein said searching involves applying both rigid motion and deformation operators to that reference 3D representation to generate multiple versions of the reference 3D representation, and for each version of the reference 3D representation, computing a measure of fit between that version of the reference 3D representation and the at least one source 2D image,
wherein the best-fit 3D representation is the version of the reference 3D representation that yields a best measure of fit, and
wherein searching over rigid motions and deformations of the reference 3D representation to identify a best match reference 3D representation most resembling the at least one source 2D projection is performed without actually generating any projections.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/635,999 US20100295854A1 (en) | 2003-03-06 | 2009-12-11 | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery |
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US45242903P | 2003-03-06 | 2003-03-06 | |
US45243103P | 2003-03-06 | 2003-03-06 | |
US45243003P | 2003-03-06 | 2003-03-06 | |
US10/794,353 US7643685B2 (en) | 2003-03-06 | 2004-03-05 | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery |
US12/635,999 US20100295854A1 (en) | 2003-03-06 | 2009-12-11 | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/794,353 Continuation US7643685B2 (en) | 2003-03-06 | 2004-03-05 | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery |
Publications (1)
Publication Number | Publication Date |
---|---|
US20100295854A1 true US20100295854A1 (en) | 2010-11-25 |
Family
ID=32995971
Family Applications (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/794,353 Expired - Fee Related US7643685B2 (en) | 2003-03-06 | 2004-03-05 | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery |
US10/794,352 Expired - Fee Related US7643683B2 (en) | 2003-03-06 | 2004-03-05 | Generation of image database for multifeatured objects |
US10/794,943 Expired - Fee Related US7853085B2 (en) | 2003-03-06 | 2004-03-05 | Viewpoint-invariant detection and identification of a three-dimensional object from two-dimensional imagery |
US12/635,999 Abandoned US20100295854A1 (en) | 2003-03-06 | 2009-12-11 | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery |
Family Applications Before (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/794,353 Expired - Fee Related US7643685B2 (en) | 2003-03-06 | 2004-03-05 | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery |
US10/794,352 Expired - Fee Related US7643683B2 (en) | 2003-03-06 | 2004-03-05 | Generation of image database for multifeatured objects |
US10/794,943 Expired - Fee Related US7853085B2 (en) | 2003-03-06 | 2004-03-05 | Viewpoint-invariant detection and identification of a three-dimensional object from two-dimensional imagery |
Country Status (4)
Country | Link |
---|---|
US (4) | US7643685B2 (en) |
EP (3) | EP1599828A1 (en) |
JP (3) | JP2006520054A (en) |
WO (3) | WO2004081853A1 (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100289664A1 (en) * | 2008-10-15 | 2010-11-18 | Panasonic Corporation | Light projection device |
US20110316853A1 (en) * | 2010-06-23 | 2011-12-29 | Microsoft Corporation | Telepresence systems with viewer perspective adjustment |
US20120086783A1 (en) * | 2010-06-08 | 2012-04-12 | Raj Sareen | System and method for body scanning and avatar creation |
US20130201187A1 (en) * | 2011-08-09 | 2013-08-08 | Xiaofeng Tong | Image-based multi-view 3d face generation |
US8570343B2 (en) * | 2010-04-20 | 2013-10-29 | Dassault Systemes | Automatic generation of 3D models from packaged goods product images |
WO2014043755A1 (en) * | 2012-09-19 | 2014-03-27 | Commonwealth Scientific And Industrial Research Organisation | System and method of generating a non-rigid model |
US20160078663A1 (en) * | 2010-06-08 | 2016-03-17 | Styku, Inc. | Cloud server body scan data system |
US20160088284A1 (en) * | 2010-06-08 | 2016-03-24 | Styku, Inc. | Method and system for determining biometrics from body surface imaging technology |
US20160247017A1 (en) * | 2010-06-08 | 2016-08-25 | Raj Sareen | Method and system for body scanning and display of biometric data |
US20160275688A1 (en) * | 2013-11-01 | 2016-09-22 | The Research Foundation For The State University Of New York | Method for Measuring the Interior Three-Dimensional Movement, Stress and Strain of an Object |
CN109145935A (en) * | 2017-06-15 | 2019-01-04 | 欧姆龙株式会社 | Template construct devices and methods therefor, object identification processing unit and storage medium |
US10269175B2 (en) | 2015-07-14 | 2019-04-23 | Samsung Electronics Co., Ltd. | Three dimensional content generating apparatus and three dimensional content generating method thereof |
US20190311488A1 (en) * | 2010-06-08 | 2019-10-10 | Styku, LLC | Method and system for wireless ultra-low footprint body scanning |
US11069121B2 (en) * | 2017-08-31 | 2021-07-20 | Sony Group Corporation | Methods, devices and computer program products for creating textured 3D images |
WO2021237169A1 (en) * | 2020-05-21 | 2021-11-25 | Sareen Iva | Online garment design and collaboration and virtual try-on system and method |
US11244223B2 (en) * | 2010-06-08 | 2022-02-08 | Iva Sareen | Online garment design and collaboration system and method |
US20220215224A1 (en) * | 2017-06-22 | 2022-07-07 | Iva Sareen | Online garment design and collaboration system and method |
Families Citing this family (154)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20040071145A (en) * | 2001-11-24 | 2004-08-11 | 티디브이 테크놀러지스 코포레이션 | Generation of a stereo image sequence from a 2d image sequence |
US7421098B2 (en) * | 2002-10-07 | 2008-09-02 | Technion Research & Development Foundation Ltd. | Facial recognition and the open mouth problem |
US6947579B2 (en) * | 2002-10-07 | 2005-09-20 | Technion Research & Development Foundation Ltd. | Three-dimensional face recognition |
JP4556873B2 (en) * | 2003-10-21 | 2010-10-06 | 日本電気株式会社 | Image collation system and image collation method |
US20050152504A1 (en) * | 2004-01-13 | 2005-07-14 | Ang Shih | Method and apparatus for automated tomography inspection |
EP1766552A2 (en) * | 2004-06-23 | 2007-03-28 | Strider Labs, Inc. | System and method for 3d object recognition using range and intensity |
US7542034B2 (en) | 2004-09-23 | 2009-06-02 | Conversion Works, Inc. | System and method for processing video images |
US7480414B2 (en) * | 2004-10-14 | 2009-01-20 | International Business Machines Corporation | Method and apparatus for object normalization using object classification |
CN102599715B (en) * | 2004-10-22 | 2014-11-05 | 株式会社资生堂 | Lip categorizing method |
US20060127852A1 (en) * | 2004-12-14 | 2006-06-15 | Huafeng Wen | Image based orthodontic treatment viewing system |
KR100601989B1 (en) * | 2005-02-07 | 2006-07-18 | 삼성전자주식회사 | Apparatus and method for estimating 3d face shape from 2d image and computer readable media for storing computer program |
US8213677B2 (en) * | 2005-03-04 | 2012-07-03 | National University Corporation NARA Institute of Science and Technology | Motion measuring device, motion measuring system, in-vehicle device, motion measuring method, motion measurement program, and computer-readable storage medium |
US8732025B2 (en) | 2005-05-09 | 2014-05-20 | Google Inc. | System and method for enabling image recognition and searching of remote content on display |
US7783135B2 (en) | 2005-05-09 | 2010-08-24 | Like.Com | System and method for providing objectified image renderings using recognition information from images |
US7945099B2 (en) | 2005-05-09 | 2011-05-17 | Like.Com | System and method for use of images with recognition analysis |
US7660468B2 (en) | 2005-05-09 | 2010-02-09 | Like.Com | System and method for enabling image searching using manual enrichment, classification, and/or segmentation |
US7519200B2 (en) | 2005-05-09 | 2009-04-14 | Like.Com | System and method for enabling the use of captured images through recognition |
US7657126B2 (en) * | 2005-05-09 | 2010-02-02 | Like.Com | System and method for search portions of objects in images and features thereof |
US20080177640A1 (en) | 2005-05-09 | 2008-07-24 | Salih Burak Gokturk | System and method for using image analysis and search in e-commerce |
US7760917B2 (en) | 2005-05-09 | 2010-07-20 | Like.Com | Computer-implemented method for performing similarity searches |
CA2608119A1 (en) | 2005-05-11 | 2006-11-16 | Optosecurity Inc. | Method and system for screening luggage items, cargo containers or persons |
US7991242B2 (en) | 2005-05-11 | 2011-08-02 | Optosecurity Inc. | Apparatus, method and system for screening receptacles and persons, having image distortion correction functionality |
WO2006119629A1 (en) * | 2005-05-11 | 2006-11-16 | Optosecurity Inc. | Database of target objects suitable for use in screening receptacles or people and method and apparatus for generating same |
US7929775B2 (en) * | 2005-06-16 | 2011-04-19 | Strider Labs, Inc. | System and method for recognition in 2D images using 3D class models |
JP2007064836A (en) * | 2005-08-31 | 2007-03-15 | Kyushu Institute Of Technology | Algorithm for automating camera calibration |
US20070080967A1 (en) * | 2005-10-11 | 2007-04-12 | Animetrics Inc. | Generation of normalized 2D imagery and ID systems via 2D to 3D lifting of multifeatured objects |
US7961937B2 (en) * | 2005-10-26 | 2011-06-14 | Hewlett-Packard Development Company, L.P. | Pre-normalization data classification |
US8094928B2 (en) | 2005-11-14 | 2012-01-10 | Microsoft Corporation | Stereo video for gaming |
US20070124330A1 (en) * | 2005-11-17 | 2007-05-31 | Lydia Glass | Methods of rendering information services and related devices |
TW200725433A (en) * | 2005-12-29 | 2007-07-01 | Ind Tech Res Inst | Three-dimensional face recognition system and method thereof |
CN101405104B (en) | 2006-01-23 | 2011-05-25 | 海-科产品公司 | Key duplication machine |
US9101990B2 (en) | 2006-01-23 | 2015-08-11 | Hy-Ko Products | Key duplication machine |
WO2007092629A2 (en) * | 2006-02-09 | 2007-08-16 | Nms Communications Corporation | Smooth morphing between personal video calling avatars |
US8571272B2 (en) * | 2006-03-12 | 2013-10-29 | Google Inc. | Techniques for enabling or establishing the use of face recognition algorithms |
US9690979B2 (en) | 2006-03-12 | 2017-06-27 | Google Inc. | Techniques for enabling or establishing the use of face recognition algorithms |
JP4362489B2 (en) * | 2006-03-29 | 2009-11-11 | 日本電気株式会社 | 3D face data registration system, 3D face data registration method, and registration processing program |
JP4785598B2 (en) * | 2006-04-07 | 2011-10-05 | 株式会社日立製作所 | Similar shape search device |
US7899232B2 (en) | 2006-05-11 | 2011-03-01 | Optosecurity Inc. | Method and apparatus for providing threat image projection (TIP) in a luggage screening system, and luggage screening system implementing same |
US8494210B2 (en) | 2007-03-30 | 2013-07-23 | Optosecurity Inc. | User interface for use in security screening providing image enhancement capabilities and apparatus for implementing same |
US8233702B2 (en) * | 2006-08-18 | 2012-07-31 | Google Inc. | Computer implemented technique for analyzing images |
US8437535B2 (en) | 2006-09-19 | 2013-05-07 | Roboticvisiontech Llc | System and method of determining object pose |
TWI332639B (en) * | 2006-09-27 | 2010-11-01 | Compal Electronics Inc | Method for displaying expressional image |
US7966567B2 (en) * | 2007-07-12 | 2011-06-21 | Center'd Corp. | Character expression in a geo-spatial environment |
US20080181485A1 (en) * | 2006-12-15 | 2008-07-31 | Beis Jeffrey S | System and method of identifying objects |
JP5024067B2 (en) * | 2007-01-19 | 2012-09-12 | コニカミノルタホールディングス株式会社 | Face authentication system, method and program |
US8655052B2 (en) | 2007-01-26 | 2014-02-18 | Intellectual Discovery Co., Ltd. | Methodology for 3D scene reconstruction from 2D image sequences |
JP2008187591A (en) * | 2007-01-31 | 2008-08-14 | Fujifilm Corp | Imaging apparatus and imaging method |
US20080228449A1 (en) * | 2007-03-12 | 2008-09-18 | Conversion Works, Inc. | Systems and methods for 2-d to 3-d conversion using depth access segments to define an object |
US8274530B2 (en) | 2007-03-12 | 2012-09-25 | Conversion Works, Inc. | Systems and methods for filling occluded information for 2-D to 3-D conversion |
US20080225045A1 (en) * | 2007-03-12 | 2008-09-18 | Conversion Works, Inc. | Systems and methods for 2-d to 3-d image conversion using mask to model, or model to mask, conversion |
JP4337064B2 (en) * | 2007-04-04 | 2009-09-30 | ソニー株式会社 | Information processing apparatus, information processing method, and program |
JP5096776B2 (en) * | 2007-04-04 | 2012-12-12 | キヤノン株式会社 | Image processing apparatus and image search method |
NO327279B1 (en) * | 2007-05-22 | 2009-06-02 | Metaio Gmbh | Camera position estimation device and method for augmented reality imaging |
US8416981B2 (en) | 2007-07-29 | 2013-04-09 | Google Inc. | System and method for displaying contextual supplemental content based on image content |
DE602007003849D1 (en) * | 2007-10-11 | 2010-01-28 | Mvtec Software Gmbh | System and method for 3D object recognition |
US8059888B2 (en) * | 2007-10-30 | 2011-11-15 | Microsoft Corporation | Semi-automatic plane extrusion for 3D modeling |
US8862582B2 (en) * | 2007-11-15 | 2014-10-14 | At&T Intellectual Property I, L.P. | System and method of organizing images |
US8190604B2 (en) * | 2008-04-03 | 2012-05-29 | Microsoft Corporation | User intention modeling for interactive image retrieval |
US20100017033A1 (en) * | 2008-07-18 | 2010-01-21 | Remus Boca | Robotic systems with user operable robot control terminals |
JP5253066B2 (en) * | 2008-09-24 | 2013-07-31 | キヤノン株式会社 | Position and orientation measurement apparatus and method |
US8368689B2 (en) * | 2008-09-25 | 2013-02-05 | Siemens Product Lifecycle Management Software Inc. | System, method, and computer program product for radial functions and distributions of three dimensional object models |
US8559699B2 (en) | 2008-10-10 | 2013-10-15 | Roboticvisiontech Llc | Methods and apparatus to facilitate operations in image based systems |
US8159327B2 (en) * | 2008-11-13 | 2012-04-17 | Visa International Service Association | Device including authentication glyph |
JP2010186288A (en) * | 2009-02-12 | 2010-08-26 | Seiko Epson Corp | Image processing for changing predetermined texture characteristic amount of face image |
US9740921B2 (en) | 2009-02-26 | 2017-08-22 | Tko Enterprises, Inc. | Image processing sensor systems |
US9277878B2 (en) * | 2009-02-26 | 2016-03-08 | Tko Enterprises, Inc. | Image processing sensor systems |
US9293017B2 (en) * | 2009-02-26 | 2016-03-22 | Tko Enterprises, Inc. | Image processing sensor systems |
US8644619B2 (en) * | 2009-05-01 | 2014-02-04 | Hy-Ko Products Company | Key blank identification system with groove scanning |
US8634655B2 (en) | 2009-05-01 | 2014-01-21 | Hy-Ko Products Company | Key blank identification system with bitting analysis |
WO2010131371A1 (en) * | 2009-05-12 | 2010-11-18 | Toyota Jidosha Kabushiki Kaisha | Object recognition method, object recognition apparatus, and autonomous mobile robot |
US20100313141A1 (en) * | 2009-06-03 | 2010-12-09 | Tianli Yu | System and Method for Learning User Genres and Styles and for Matching Products to User Preferences |
US8553972B2 (en) * | 2009-07-06 | 2013-10-08 | Samsung Electronics Co., Ltd. | Apparatus, method and computer-readable medium generating depth map |
US20110025689A1 (en) * | 2009-07-29 | 2011-02-03 | Microsoft Corporation | Auto-Generating A Visual Representation |
US9366780B2 (en) | 2009-10-08 | 2016-06-14 | Precision Energy Services, Inc. | Steerable magnetic dipole antenna for measurement while drilling applications |
US8604796B2 (en) * | 2009-10-08 | 2013-12-10 | Precision Energy Services, Inc. | Steerable magnetic dipole antenna for measurement-while-drilling applications |
JP2011090466A (en) * | 2009-10-21 | 2011-05-06 | Sony Corp | Information processing apparatus, method, and program |
KR20110070056A (en) * | 2009-12-18 | 2011-06-24 | 한국전자통신연구원 | Method and apparatus for easy and intuitive generation of user-customized 3d avatar with high-quality |
US20110268365A1 (en) * | 2010-04-30 | 2011-11-03 | Acer Incorporated | 3d hand posture recognition system and vision based hand posture recognition method thereof |
EP2385483B1 (en) | 2010-05-07 | 2012-11-21 | MVTec Software GmbH | Recognition and pose determination of 3D objects in 3D scenes using geometric point pair descriptors and the generalized Hough Transform |
US8452721B2 (en) * | 2010-06-15 | 2013-05-28 | Nvidia Corporation | Region of interest tracking for fluid simulation |
US8416990B2 (en) | 2010-08-17 | 2013-04-09 | Microsoft Corporation | Hierarchical video sub-volume search |
US8432392B2 (en) * | 2010-09-02 | 2013-04-30 | Samsung Electronics Co., Ltd. | Display system with image conversion mechanism and method of operation thereof |
US9317533B2 (en) | 2010-11-02 | 2016-04-19 | Microsoft Technology Licensing, Inc. | Adaptive image retrieval database |
US8463045B2 (en) | 2010-11-10 | 2013-06-11 | Microsoft Corporation | Hierarchical sparse representation for image retrieval |
US8711210B2 (en) * | 2010-12-14 | 2014-04-29 | Raytheon Company | Facial recognition using a sphericity metric |
WO2012082077A2 (en) * | 2010-12-17 | 2012-06-21 | Agency For Science, Technology And Research | Pose-independent 3d face reconstruction from a sample 2d face image |
US9959644B2 (en) * | 2010-12-21 | 2018-05-01 | Qualcomm Incorporated | Computerized method and device for annotating at least one feature of an image of a view |
DE102011008074A1 (en) * | 2011-01-07 | 2012-07-12 | Martin Tank | Method and dental restorative system for determining dental restorations |
US9952046B1 (en) | 2011-02-15 | 2018-04-24 | Guardvant, Inc. | Cellular phone and personal protective equipment usage monitoring system |
US9198575B1 (en) | 2011-02-15 | 2015-12-01 | Guardvant, Inc. | System and method for determining a level of operator fatigue |
US8988512B2 (en) | 2011-04-14 | 2015-03-24 | Mediatek Inc. | Method for adjusting playback of multimedia content according to detection result of user status and related apparatus thereof |
WO2013026048A2 (en) * | 2011-08-18 | 2013-02-21 | Utherverse Digital, Inc. | Systems and methods of virtual world interaction |
JP5143262B1 (en) * | 2011-08-30 | 2013-02-13 | 株式会社東芝 | 3D image processing apparatus and 3D image processing method |
KR102067367B1 (en) | 2011-09-07 | 2020-02-11 | 라피스캔 시스템스, 인코포레이티드 | X-ray inspection method that integrates manifest data with imaging/detection processing |
US9236024B2 (en) | 2011-12-06 | 2016-01-12 | Glasses.Com Inc. | Systems and methods for obtaining a pupillary distance measurement using a mobile computing device |
KR20130063310A (en) * | 2011-12-06 | 2013-06-14 | 엘지전자 주식회사 | Mobile terminal and control method for mobile terminal |
US10013787B2 (en) | 2011-12-12 | 2018-07-03 | Faceshift Ag | Method for facial animation |
US9904843B2 (en) * | 2012-03-27 | 2018-02-27 | Nec Corporation | Information processing device, information processing method, and program |
US9286715B2 (en) | 2012-05-23 | 2016-03-15 | Glasses.Com Inc. | Systems and methods for adjusting a virtual try-on |
US9483853B2 (en) | 2012-05-23 | 2016-11-01 | Glasses.Com Inc. | Systems and methods to display rendered images |
US9378584B2 (en) | 2012-05-23 | 2016-06-28 | Glasses.Com Inc. | Systems and methods for rendering virtual try-on products |
US9141848B2 (en) * | 2012-09-04 | 2015-09-22 | Intel Corporation | Automatic media distribution |
US10678259B1 (en) * | 2012-09-13 | 2020-06-09 | Waymo Llc | Use of a reference image to detect a road obstacle |
US9020982B2 (en) | 2012-10-15 | 2015-04-28 | Qualcomm Incorporated | Detection of planar targets under steep angles |
US9743002B2 (en) * | 2012-11-19 | 2017-08-22 | Magna Electronics Inc. | Vehicle vision system with enhanced display functions |
WO2014094199A1 (en) * | 2012-12-17 | 2014-06-26 | Intel Corporation | Facial movement based avatar animation |
US9990373B2 (en) * | 2013-02-06 | 2018-06-05 | John A. Fortkort | Creation and geospatial placement of avatars based on real-world interactions |
US9381426B1 (en) * | 2013-03-15 | 2016-07-05 | University Of Central Florida Research Foundation, Inc. | Semi-automated digital puppetry control |
US9990004B2 (en) * | 2013-04-02 | 2018-06-05 | Samsung Dispaly Co., Ltd. | Optical detection of bending motions of a flexible display |
US9449392B2 (en) * | 2013-06-05 | 2016-09-20 | Samsung Electronics Co., Ltd. | Estimator training method and pose estimating method using depth image |
US9839761B1 (en) | 2013-07-04 | 2017-12-12 | Hal Rucker | Airflow control for pressurized air delivery |
US9355123B2 (en) | 2013-07-19 | 2016-05-31 | Nant Holdings Ip, Llc | Fast recognition algorithm processing, systems and methods |
KR101509934B1 (en) * | 2013-10-10 | 2015-04-16 | 재단법인대구경북과학기술원 | Device of a front head pose guidance, and method thereof |
US9589383B2 (en) | 2013-10-18 | 2017-03-07 | Nvidia Corporation | Unified position based solver for visual effects |
US9613449B2 (en) | 2013-10-18 | 2017-04-04 | Nvidia Corporation | Method and apparatus for simulating stiff stacks |
WO2015089115A1 (en) * | 2013-12-09 | 2015-06-18 | Nant Holdings Ip, Llc | Feature density object classification, systems and methods |
WO2015123647A1 (en) * | 2014-02-14 | 2015-08-20 | Nant Holdings Ip, Llc | Object ingestion through canonical shapes, systems and methods |
WO2016043659A1 (en) * | 2014-09-15 | 2016-03-24 | Temasek Life Sciences Laboratory Limited | Image recognition system and method |
US9710699B2 (en) * | 2014-10-31 | 2017-07-18 | Irvine Sensors Corp. | Three dimensional recognition from unscripted sources technology (TRUST) |
RU2582852C1 (en) * | 2015-01-21 | 2016-04-27 | Общество с ограниченной ответственностью "Вокорд СофтЛаб" (ООО "Вокорд СофтЛаб") | Automatic construction of 3d model of face based on series of 2d images or movie |
US9818041B2 (en) | 2015-08-03 | 2017-11-14 | Hy-Ko Products Company | High security key scanning system |
US20170103563A1 (en) * | 2015-10-07 | 2017-04-13 | Victor Erukhimov | Method of creating an animated realistic 3d model of a person |
KR101755248B1 (en) * | 2016-01-27 | 2017-07-07 | (주)에이아이퍼스트 | Method and system of generating 3D model and mobile device for the same |
US9868212B1 (en) * | 2016-02-18 | 2018-01-16 | X Development Llc | Methods and apparatus for determining the pose of an object based on point cloud data |
EP3420563A4 (en) | 2016-02-22 | 2020-03-11 | Rapiscan Systems, Inc. | Systems and methods for detecting threats and contraband in cargo |
US20170280130A1 (en) * | 2016-03-25 | 2017-09-28 | Microsoft Technology Licensing, Llc | 2d video analysis for 3d modeling |
JP6744747B2 (en) * | 2016-04-01 | 2020-08-19 | キヤノン株式会社 | Information processing apparatus and control method thereof |
WO2017209777A1 (en) * | 2016-06-03 | 2017-12-07 | Oculus Vr, Llc | Face and eye tracking and facial animation using facial sensors within a head-mounted display |
US10474932B2 (en) * | 2016-09-01 | 2019-11-12 | Uptake Technologies, Inc. | Detection of anomalies in multivariate data |
WO2018053703A1 (en) * | 2016-09-21 | 2018-03-29 | Intel Corporation | Estimating accurate face shape and texture from an image |
FR3060170B1 (en) * | 2016-12-14 | 2019-05-24 | Smart Me Up | OBJECT RECOGNITION SYSTEM BASED ON AN ADAPTIVE 3D GENERIC MODEL |
US20180357819A1 (en) * | 2017-06-13 | 2018-12-13 | Fotonation Limited | Method for generating a set of annotated images |
EP3420903B1 (en) * | 2017-06-29 | 2019-10-23 | Siemens Healthcare GmbH | Visualisation of at least one indicator |
US10870056B2 (en) * | 2017-11-01 | 2020-12-22 | Sony Interactive Entertainment Inc. | Emoji-based communications derived from facial features during game play |
US20190143221A1 (en) * | 2017-11-15 | 2019-05-16 | Sony Interactive Entertainment America Llc | Generation and customization of personalized avatars |
US10783346B2 (en) * | 2017-12-11 | 2020-09-22 | Invensense, Inc. | Enhancing quality of a fingerprint image |
CN109918976B (en) * | 2017-12-13 | 2021-04-02 | 航天信息股份有限公司 | Portrait comparison algorithm fusion method and device thereof |
US11099708B2 (en) | 2017-12-15 | 2021-08-24 | Hewlett-Packard Development Company, L.P. | Patterns for locations on three-dimensional objects |
CN111742351A (en) | 2018-02-23 | 2020-10-02 | 三星电子株式会社 | Electronic device for generating image including 3D avatar reflecting face motion through 3D avatar corresponding to face and method of operating the same |
WO2019178054A1 (en) * | 2018-03-12 | 2019-09-19 | Carnegie Mellon University | Pose invariant face recognition |
CN108549848B (en) * | 2018-03-27 | 2022-02-25 | 百度在线网络技术(北京)有限公司 | Method and apparatus for outputting information |
CN109118569B (en) * | 2018-08-16 | 2023-03-10 | Oppo广东移动通信有限公司 | Rendering method and device based on three-dimensional model |
KR102615196B1 (en) | 2018-08-21 | 2023-12-18 | 삼성전자주식회사 | Method and device to train object detection model |
US10621788B1 (en) * | 2018-09-25 | 2020-04-14 | Sony Corporation | Reconstructing three-dimensional (3D) human body model based on depth points-to-3D human body model surface distance |
US10489683B1 (en) * | 2018-12-17 | 2019-11-26 | Bodygram, Inc. | Methods and systems for automatic generation of massive training data sets from 3D models for training deep learning networks |
CN109816704B (en) * | 2019-01-28 | 2021-08-03 | 北京百度网讯科技有限公司 | Method and device for acquiring three-dimensional information of object |
US11386636B2 (en) | 2019-04-04 | 2022-07-12 | Datalogic Usa, Inc. | Image preprocessing for optical character recognition |
EP3731132A1 (en) * | 2019-04-25 | 2020-10-28 | XRSpace CO., LTD. | Method of generating 3d facial model for an avatar and related device |
US10992619B2 (en) * | 2019-04-30 | 2021-04-27 | Snap Inc. | Messaging system with avatar generation |
US10803301B1 (en) * | 2019-08-02 | 2020-10-13 | Capital One Services, Llc | Detecting fraud in image recognition systems |
WO2021084662A1 (en) * | 2019-10-30 | 2021-05-06 | 日本電気株式会社 | Checking assistance device, checking assistance method, and computer-readable recording medium |
WO2021106154A1 (en) * | 2019-11-28 | 2021-06-03 | 三菱電機株式会社 | Workpiece image searching device, workpiece image searching method, and machine learning device |
US11810256B2 (en) * | 2021-11-11 | 2023-11-07 | Qualcomm Incorporated | Image modification techniques |
WO2023175648A1 (en) * | 2022-03-14 | 2023-09-21 | 三菱電機株式会社 | Learning image generation device and learning image generation method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6002782A (en) * | 1997-11-12 | 1999-12-14 | Unisys Corporation | System and method for recognizing a 3-D object by generating a 2-D image of the object from a transformed 3-D model |
US20010020946A1 (en) * | 2000-03-10 | 2001-09-13 | Minolta Co., Ltd. | Method and apparatus for data processing recognizing an object represented as two-dimensional image |
US6381346B1 (en) * | 1997-12-01 | 2002-04-30 | Wheeling Jesuit University | Three-dimensional face identification system |
US6434278B1 (en) * | 1997-09-23 | 2002-08-13 | Enroute, Inc. | Generating three-dimensional models of objects defined by two-dimensional image data |
US6556196B1 (en) * | 1999-03-19 | 2003-04-29 | Max-Planck-Gesellschaft Zur Forderung Der Wissenschaften E.V. | Method and apparatus for the processing of images |
US6956569B1 (en) * | 2000-03-30 | 2005-10-18 | Nec Corporation | Method for matching a two dimensional image to one of a plurality of three dimensional candidate models contained in a database |
US20070031028A1 (en) * | 2005-06-20 | 2007-02-08 | Thomas Vetter | Estimating 3d shape and texture of a 3d object based on a 2d image of the 3d object |
Family Cites Families (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5159361A (en) * | 1989-03-09 | 1992-10-27 | Par Technology Corporation | Method and apparatus for obtaining the topography of an object |
US5825936A (en) * | 1994-09-22 | 1998-10-20 | University Of South Florida | Image analyzing device using adaptive criteria |
US5761638A (en) * | 1995-03-17 | 1998-06-02 | Us West Inc | Telephone network apparatus and method using echo delay and attenuation |
US5742291A (en) * | 1995-05-09 | 1998-04-21 | Synthonics Incorporated | Method and apparatus for creation of three-dimensional wire frames |
US5844573A (en) * | 1995-06-07 | 1998-12-01 | Massachusetts Institute Of Technology | Image compression by pointwise prototype correspondence using shape and texture information |
US6226418B1 (en) * | 1997-11-07 | 2001-05-01 | Washington University | Rapid convolution based large deformation image matching via landmark and volume imagery |
US5898438A (en) * | 1996-11-12 | 1999-04-27 | Ford Global Technologies, Inc. | Texture mapping of photographic images to CAD surfaces |
US6094199A (en) * | 1997-05-23 | 2000-07-25 | University Of Washington | 3D objects morphing employing skeletons indicating symmetric differences to define intermediate objects used in morphing |
US5990901A (en) * | 1997-06-27 | 1999-11-23 | Microsoft Corporation | Model based image editing and correction |
EP0907145A3 (en) * | 1997-10-03 | 2003-03-26 | Nippon Telegraph and Telephone Corporation | Method and equipment for extracting image features from image sequence |
US6249600B1 (en) * | 1997-11-07 | 2001-06-19 | The Trustees Of Columbia University In The City Of New York | System and method for generation of a three-dimensional solid model |
US6362833B2 (en) * | 1998-04-08 | 2002-03-26 | Intel Corporation | Method and apparatus for progressively constructing a series of morphs between two-dimensional or three-dimensional models |
JP3467725B2 (en) * | 1998-06-02 | 2003-11-17 | 富士通株式会社 | Image shadow removal method, image processing apparatus, and recording medium |
US6366282B1 (en) * | 1998-09-08 | 2002-04-02 | Intel Corporation | Method and apparatus for morphing objects by subdividing and mapping portions of the objects |
IT1315446B1 (en) * | 1998-10-02 | 2003-02-11 | Cselt Centro Studi Lab Telecom | PROCEDURE FOR THE CREATION OF THREE-DIMENSIONAL FACIAL MODELS TO START FROM FACE IMAGES. |
JP4025442B2 (en) * | 1998-12-01 | 2007-12-19 | 富士通株式会社 | 3D model conversion apparatus and method |
US6296317B1 (en) * | 1999-10-29 | 2001-10-02 | Carnegie Mellon University | Vision-based motion sensor for mining machine control |
GB0004165D0 (en) | 2000-02-22 | 2000-04-12 | Digimask Limited | System for virtual three-dimensional object creation and use |
US6807290B2 (en) | 2000-03-09 | 2004-10-19 | Microsoft Corporation | Rapid computer modeling of faces for animation |
JP2001283216A (en) | 2000-04-03 | 2001-10-12 | Nec Corp | Image collating device, image collating method and recording medium in which its program is recorded |
JP4387552B2 (en) * | 2000-04-27 | 2009-12-16 | 富士通株式会社 | Image verification processing system |
US6853745B1 (en) | 2000-11-03 | 2005-02-08 | Nec Laboratories America, Inc. | Lambertian reflectance and linear subspaces |
US6975750B2 (en) * | 2000-12-01 | 2005-12-13 | Microsoft Corp. | System and method for face recognition using synthesized training images |
GB2383915B (en) * | 2001-11-23 | 2005-09-28 | Canon Kk | Method and apparatus for generating models of individuals |
US7221809B2 (en) * | 2001-12-17 | 2007-05-22 | Genex Technologies, Inc. | Face recognition system and method |
AU2003219926A1 (en) * | 2002-02-26 | 2003-09-09 | Canesta, Inc. | Method and apparatus for recognizing objects |
FR2849241B1 (en) * | 2002-12-20 | 2005-06-24 | Biospace Instr | RADIOGRAPHIC IMAGING METHOD AND DEVICE |
AU2003220950A1 (en) | 2003-03-28 | 2004-10-25 | Fujitsu Limited | Imager and personal idenfification system |
-
2004
- 2004-03-05 EP EP04717974A patent/EP1599828A1/en not_active Withdrawn
- 2004-03-05 WO PCT/US2004/006604 patent/WO2004081853A1/en active Application Filing
- 2004-03-05 EP EP04718062A patent/EP1599830A1/en not_active Withdrawn
- 2004-03-05 US US10/794,353 patent/US7643685B2/en not_active Expired - Fee Related
- 2004-03-05 JP JP2006509130A patent/JP2006520054A/en active Pending
- 2004-03-05 JP JP2006509131A patent/JP2006520055A/en active Pending
- 2004-03-05 JP JP2006509187A patent/JP2006522411A/en active Pending
- 2004-03-05 EP EP04717979A patent/EP1599829A1/en not_active Withdrawn
- 2004-03-05 WO PCT/US2004/006614 patent/WO2004081854A1/en active Application Filing
- 2004-03-05 US US10/794,352 patent/US7643683B2/en not_active Expired - Fee Related
- 2004-03-05 US US10/794,943 patent/US7853085B2/en not_active Expired - Fee Related
- 2004-03-05 WO PCT/US2004/006827 patent/WO2004081855A1/en active Application Filing
-
2009
- 2009-12-11 US US12/635,999 patent/US20100295854A1/en not_active Abandoned
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6434278B1 (en) * | 1997-09-23 | 2002-08-13 | Enroute, Inc. | Generating three-dimensional models of objects defined by two-dimensional image data |
US6002782A (en) * | 1997-11-12 | 1999-12-14 | Unisys Corporation | System and method for recognizing a 3-D object by generating a 2-D image of the object from a transformed 3-D model |
US6381346B1 (en) * | 1997-12-01 | 2002-04-30 | Wheeling Jesuit University | Three-dimensional face identification system |
US6556196B1 (en) * | 1999-03-19 | 2003-04-29 | Max-Planck-Gesellschaft Zur Forderung Der Wissenschaften E.V. | Method and apparatus for the processing of images |
US20010020946A1 (en) * | 2000-03-10 | 2001-09-13 | Minolta Co., Ltd. | Method and apparatus for data processing recognizing an object represented as two-dimensional image |
US6956569B1 (en) * | 2000-03-30 | 2005-10-18 | Nec Corporation | Method for matching a two dimensional image to one of a plurality of three dimensional candidate models contained in a database |
US20070031028A1 (en) * | 2005-06-20 | 2007-02-08 | Thomas Vetter | Estimating 3d shape and texture of a 3d object based on a 2d image of the 3d object |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8446288B2 (en) * | 2008-10-15 | 2013-05-21 | Panasonic Corporation | Light projection device |
US20100289664A1 (en) * | 2008-10-15 | 2010-11-18 | Panasonic Corporation | Light projection device |
US8570343B2 (en) * | 2010-04-20 | 2013-10-29 | Dassault Systemes | Automatic generation of 3D models from packaged goods product images |
US10702216B2 (en) * | 2010-06-08 | 2020-07-07 | Styku, LLC | Method and system for body scanning and display of biometric data |
US11244223B2 (en) * | 2010-06-08 | 2022-02-08 | Iva Sareen | Online garment design and collaboration system and method |
US20120086783A1 (en) * | 2010-06-08 | 2012-04-12 | Raj Sareen | System and method for body scanning and avatar creation |
US20190311488A1 (en) * | 2010-06-08 | 2019-10-10 | Styku, LLC | Method and system for wireless ultra-low footprint body scanning |
US11640672B2 (en) * | 2010-06-08 | 2023-05-02 | Styku Llc | Method and system for wireless ultra-low footprint body scanning |
US20160078663A1 (en) * | 2010-06-08 | 2016-03-17 | Styku, Inc. | Cloud server body scan data system |
US20160088284A1 (en) * | 2010-06-08 | 2016-03-24 | Styku, Inc. | Method and system for determining biometrics from body surface imaging technology |
US20160247017A1 (en) * | 2010-06-08 | 2016-08-25 | Raj Sareen | Method and system for body scanning and display of biometric data |
US10628729B2 (en) * | 2010-06-08 | 2020-04-21 | Styku, LLC | System and method for body scanning and avatar creation |
US10628666B2 (en) * | 2010-06-08 | 2020-04-21 | Styku, LLC | Cloud server body scan data system |
US8928659B2 (en) * | 2010-06-23 | 2015-01-06 | Microsoft Corporation | Telepresence systems with viewer perspective adjustment |
US20110316853A1 (en) * | 2010-06-23 | 2011-12-29 | Microsoft Corporation | Telepresence systems with viewer perspective adjustment |
US20130201187A1 (en) * | 2011-08-09 | 2013-08-08 | Xiaofeng Tong | Image-based multi-view 3d face generation |
WO2014043755A1 (en) * | 2012-09-19 | 2014-03-27 | Commonwealth Scientific And Industrial Research Organisation | System and method of generating a non-rigid model |
AU2013317700B2 (en) * | 2012-09-19 | 2019-01-17 | Commonwealth Scientific And Industrial Research Organisation | System and method of generating a non-rigid model |
TWI666592B (en) * | 2012-09-19 | 2019-07-21 | 澳洲聯邦科學暨工業研究組織 | System and method of generating a non-rigid model |
US9928635B2 (en) | 2012-09-19 | 2018-03-27 | Commonwealth Scientific And Industrial Research Organisation | System and method of generating a non-rigid model |
US20160275688A1 (en) * | 2013-11-01 | 2016-09-22 | The Research Foundation For The State University Of New York | Method for Measuring the Interior Three-Dimensional Movement, Stress and Strain of an Object |
US10013767B2 (en) * | 2013-11-01 | 2018-07-03 | The Research Foundation For The State University Of New York | Method for measuring the interior three-dimensional movement, stress and strain of an object |
US11010967B2 (en) | 2015-07-14 | 2021-05-18 | Samsung Electronics Co., Ltd. | Three dimensional content generating apparatus and three dimensional content generating method thereof |
US10269175B2 (en) | 2015-07-14 | 2019-04-23 | Samsung Electronics Co., Ltd. | Three dimensional content generating apparatus and three dimensional content generating method thereof |
CN109145935A (en) * | 2017-06-15 | 2019-01-04 | 欧姆龙株式会社 | Template construct devices and methods therefor, object identification processing unit and storage medium |
US20220215224A1 (en) * | 2017-06-22 | 2022-07-07 | Iva Sareen | Online garment design and collaboration system and method |
US11948057B2 (en) * | 2017-06-22 | 2024-04-02 | Iva Sareen | Online garment design and collaboration system and method |
US11069121B2 (en) * | 2017-08-31 | 2021-07-20 | Sony Group Corporation | Methods, devices and computer program products for creating textured 3D images |
WO2021237169A1 (en) * | 2020-05-21 | 2021-11-25 | Sareen Iva | Online garment design and collaboration and virtual try-on system and method |
Also Published As
Publication number | Publication date |
---|---|
US20040175039A1 (en) | 2004-09-09 |
JP2006522411A (en) | 2006-09-28 |
WO2004081854A1 (en) | 2004-09-23 |
US20040175041A1 (en) | 2004-09-09 |
WO2004081855A1 (en) | 2004-09-23 |
US20040190775A1 (en) | 2004-09-30 |
JP2006520055A (en) | 2006-08-31 |
US7643685B2 (en) | 2010-01-05 |
JP2006520054A (en) | 2006-08-31 |
EP1599828A1 (en) | 2005-11-30 |
US7853085B2 (en) | 2010-12-14 |
WO2004081853A1 (en) | 2004-09-23 |
EP1599830A1 (en) | 2005-11-30 |
US7643683B2 (en) | 2010-01-05 |
EP1599829A1 (en) | 2005-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7643685B2 (en) | Viewpoint-invariant image matching and generation of three-dimensional models from two-dimensional imagery | |
Blanz et al. | Face identification across different poses and illuminations with a 3d morphable model | |
Dai et al. | A 3d morphable model of craniofacial shape and texture variation | |
US7876931B2 (en) | Face recognition system and method | |
Gu et al. | 3D alignment of face in a single image | |
US9400921B2 (en) | Method and system using a data-driven model for monocular face tracking | |
US6556196B1 (en) | Method and apparatus for the processing of images | |
JP4466951B2 (en) | Alignment of 3D face shape | |
US9275273B2 (en) | Method and system for localizing parts of an object in an image for computer vision applications | |
Romdhani et al. | Face identification by fitting a 3d morphable model using linear shape and texture error functions | |
US7095879B2 (en) | System and method for face recognition using synthesized images | |
US7212664B2 (en) | Constructing heads from 3D models and 2D silhouettes | |
US20070080967A1 (en) | Generation of normalized 2D imagery and ID systems via 2D to 3D lifting of multifeatured objects | |
WO2016011834A1 (en) | Image processing method and system | |
JP2011039869A (en) | Face image processing apparatus and computer program | |
CN108629294A (en) | Human body based on deformation pattern and face net template approximating method | |
Jin et al. | Robust 3D face modeling and reconstruction from frontal and side images | |
Ye et al. | 3d morphable face model for face animation | |
Kang et al. | Appearance-based structure from motion using linear classes of 3-d models | |
US11080920B2 (en) | Method of displaying an object | |
JP5639499B2 (en) | Face image processing device | |
Ibikunle et al. | Face recognition using line edge mapping approach | |
Aleksandrova et al. | Approach for Creating a 3D Model of a Face from its 2D Image | |
US20230237753A1 (en) | Dynamic facial hair capture of a subject | |
Ferrari et al. | Statistical 3d face reconstruction with 3d morphable models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: ANIMETRICS, INC., NEW HAMPSHIRE Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:MILLER, MICHAEL I.;REEL/FRAME:025462/0950 Effective date: 20040303 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |