WO2021092229A1 - Génération de vue arbitraire - Google Patents

Génération de vue arbitraire Download PDF

Info

Publication number
WO2021092229A1
WO2021092229A1 PCT/US2020/059188 US2020059188W WO2021092229A1 WO 2021092229 A1 WO2021092229 A1 WO 2021092229A1 US 2020059188 W US2020059188 W US 2020059188W WO 2021092229 A1 WO2021092229 A1 WO 2021092229A1
Authority
WO
WIPO (PCT)
Prior art keywords
ensemble
scene
view
perspective
assets
Prior art date
Application number
PCT/US2020/059188
Other languages
English (en)
Inventor
Clarence Chui
Manu Parmar
Brook Aaron SEATON
Himanshu Jain
Original Assignee
Outward, Inc.
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from US17/089,597 external-priority patent/US11972522B2/en
Application filed by Outward, Inc. filed Critical Outward, Inc.
Priority to KR1020227015247A priority Critical patent/KR20220076514A/ko
Priority to EP20884704.6A priority patent/EP4055567A4/fr
Priority to JP2022525977A priority patent/JP2022553844A/ja
Publication of WO2021092229A1 publication Critical patent/WO2021092229A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G06T15/10—Geometric effects
    • G06T15/20—Perspective computation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G06T15/10—Geometric effects
    • G06T15/20—Perspective computation
    • G06T15/205—Image-based rendering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/04—Architectural design, interior design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/20—Indexing scheme for editing of 3D models
    • G06T2219/2004—Aligning objects, relative positioning of parts

Definitions

  • Figure 1 is a high level block diagram illustrating an embodiment of a system for generating an arbitrary view of a scene.
  • Figure 2 illustrates an example of a database asset.
  • Figure 3 is a flow chart illustrating an embodiment of a process for generating an arbitrary perspective.
  • Figures 4A-4N illustrate examples of an embodiment of an application in which independent objects are combined to generate an ensemble or composite object.
  • Figure 5 is a flow chart illustrating an embodiment of a process for generating an arbitrary ensemble view.
  • the invention can be implemented in numerous ways, including as a process; an apparatus; a system; a composition of matter; a computer program product embodied on a computer readable storage medium; and/or a processor, such as a processor configured to execute instructions stored on and/or provided by a memory coupled to the processor.
  • these implementations, or any other form that the invention may take, may be referred to as techniques.
  • the order of the steps of disclosed processes may be altered within the scope of the invention.
  • a component such as a processor or a memory described as being configured to perform a task may be implemented as a general component that is temporarily configured to perform the task at a given time or a specific component that is manufactured to perform the task.
  • the term ‘processor’ refers to one or more devices, circuits, and/or processing cores configured to process data, such as computer program instructions.
  • Figure 1 is a high level block diagram illustrating an embodiment of a system
  • arbitrary view generator 102 receives a request for an arbitrary view as input 104, generates the requested view based on existing database assets 106, and provides the generated view as output 108 in response to the input request.
  • arbitrary view generator 102 may comprise a processor such as a central processing unit (CPU) or a graphical processing unit (GPU).
  • CPU central processing unit
  • GPU graphical processing unit
  • FIG. 1 The depicted configuration of system 100 in Figure 1 is provided for the purposes of explanation.
  • system 100 may comprise any other appropriate number and/or configuration of interconnected components that provide the described functionality.
  • arbitrary view generator 102 may comprise a different configuration of internal components 110-116, arbitrary view generator 102 may comprise a plurality of parallel physical and/or virtual processors, database 106 may comprise a plurality of networked databases or a cloud of assets, etc.
  • Arbitrary view request 104 comprises a request for an arbitrary perspective of a scene.
  • the requested perspective of the scene does not already exist in an assets database 106 that includes other perspectives or viewpoints of the scene.
  • arbitrary view request 104 may be received from a process or a user.
  • input 104 may be received from a user interface in response to user manipulation of a presented scene or portion thereof, such as user manipulation of the camera viewpoint of a presented scene.
  • arbitrary view request 104 may be received in response to a specification of a path of movement or travel within a virtual environment, such as a fly-through of a scene.
  • possible arbitrary views of a scene that may be requested are at least in part constrained. For example, a user may not be able to manipulate the camera viewpoint of a presented interactive scene to any random position but rather is constrained to certain positions or perspectives of the scene.
  • Database 106 stores a plurality of views of each stored asset.
  • an asset refers to a specific scene whose specification is stored in database 106 as a plurality of views.
  • a scene may comprise a single object, a plurality of objects, or a rich virtual environment.
  • database 106 stores a plurality of images corresponding to different perspectives or viewpoints of each asset.
  • the images stored in database 106 comprise high quality photographs or photorealistic renderings. Such high definition, high resolution images that populate database 106 may be captured or rendered during offline processes or obtained from external sources.
  • corresponding camera characteristics are stored with each image stored in database 106. That is, camera attributes such as relative location or position, orientation, rotation, depth information, focal length, aperture, zoom level, etc., are stored with each image.
  • camera lighting information such as shutter speed and exposure may also be stored with each image stored in database 106.
  • Figure 2 illustrates an example of a database asset.
  • seventy-three views corresponding to different angles around a chair object are captured or rendered and stored in database 106.
  • the views may be captured, for example, by rotating a camera around the chair or rotating the chair in front of a camera.
  • Relative object and camera location and orientation information is stored with each generated image.
  • Figure 2 specifically illustrates views of a scene comprising a single object.
  • Database 106 may also store a specification of a scene comprising a plurality of objects or a rich virtual environment.
  • images stored in database 106 may comprise two or three dimensions and may comprise stills or frames of an animation or video sequence.
  • arbitrary view generator 102 In response to a request for an arbitrary view of a scene 104 that does not already exist in database 106, arbitrary view generator 102 generates the requested arbitrary view from a plurality of other existing views of the scene stored in database 106.
  • asset management engine 110 of arbitrary view generator 102 manages database 106.
  • asset management engine 110 may facilitate storage and retrieval of data in database 106.
  • asset management engine 110 identifies and obtains a plurality of other existing views of the scene from database 106. In some embodiments, asset management engine 110 retrieves all existing views of the scene from database 106.
  • asset management engine 110 may select and retrieve a subset of the existing views, e.g., that are closest to the requested arbitrary view.
  • asset management engine 110 is configured to intelligently select a subset of existing views from which pixels may be harvested to generate the requested arbitrary view.
  • multiple existing views may be retrieved by asset management engine 110 together or as and when they are needed by other components of arbitrary view generator 102.
  • perspective transformation engine 112 of arbitrary view generator 102.
  • precise camera information is known and stored with each image stored in database 106.
  • perspective transformation engine 112 may employ any one or more appropriate mathematical techniques to transform the perspective of an existing view into the perspective of an arbitrary view.
  • the transformation of an existing view into the perspective of the arbitrary view will comprise at least some unmapped or missing pixels, i.e., at angles or positions introduced in the arbitrary view that are not present in the existing view.
  • Pixel information from a single perspective -transformed existing view will not be able to populate all pixels of a different view.
  • pixels comprising a requested arbitrary view may be harvested from a plurality of perspective-transformed existing views.
  • Merging engine 114 of arbitrary view generator 102 combines pixels from a plurality of perspective-transformed existing views to generate the requested arbitrary view.
  • all pixels comprising the arbitrary view are harvested from existing views. This may be possible, for example, if a sufficiently diverse set of existing views or perspectives of the asset under consideration is available and/or if the requested perspective is not too dissimilar from the existing perspectives.
  • any appropriate techniques may be employed to combine or merge pixels from a plurality of perspective-transformed existing views to generate the requested arbitrary view.
  • a first existing view that is closest to the requested arbitrary view is selected and retrieved from database 106 and transformed into the perspective of the requested arbitrary view. Pixels are then harvested from this perspective-transformed first existing view and used to populate corresponding pixels in the requested arbitrary view.
  • a second existing view that includes at least some of these remaining pixels is selected and retrieved from database 106 and transformed into the perspective of the requested arbitrary view.
  • Pixels that were not available from the first existing view are then harvested from this perspective-transformed second existing view and used to populate corresponding pixels in the requested arbitrary view. This process may be repeated for any number of additional existing views until all pixels of the requested arbitrary view have been populated and/or until all existing views have been exhausted or a prescribed threshold number of existing views have already been used.
  • a requested arbitrary view may include some pixels that are not available from any existing views.
  • interpolation engine 116 is configured to populate any remaining pixels of the requested arbitrary view.
  • any one or more appropriate interpolation techniques may be employed by interpolation engine 116 to generate these unpopulated pixels in the requested arbitrary view. Examples of interpolation techniques that may be employed include, for instance, linear interpolation, nearest neighbor interpolation, etc. Interpolation of pixels introduces averaging or smoothing. Overall image quality may not be significantly affected by some interpolation, but excessive interpolation may introduce unacceptable blurriness. Thus, interpolation may be desired to be sparingly used.
  • interpolation is completely avoided if all pixels of the requested arbitrary view can be obtained from existing views.
  • interpolation is introduced if the requested arbitrary view includes some pixels that are not available from any existing views.
  • the amount of interpolation needed depends on the number of existing views available, the diversity of perspectives of the existing views, and/or how different the perspective of the arbitrary view is in relation to the perspectives of the existing views.
  • seventy-three views around a chair object are stored as existing views of the chair.
  • An arbitrary view around the chair object that is different or unique from any of the stored views may be generated using a plurality of these existing views, with preferably minimal, if any, interpolation.
  • generating and storing such an exhaustive set of existing views may not be efficient or desirable.
  • a significantly smaller number of existing views covering a sufficiently diverse set of perspectives may instead be generated and stored.
  • the seventy-three views of the chair object may be decimated into a small set of a handful of views around the chair object.
  • possible arbitrary views that may be requested may at least in part be constrained.
  • a user may be restricted from moving a virtual camera associated with an interactive scene to certain positions.
  • possible arbitrary views that may be requested may be limited to arbitrary positions around the chair object but may not, for example, include arbitrary positions under the chair object since insufficient pixel data exists for the bottom of the chair object.
  • constraints on allowed arbitrary views ensure that a requested arbitrary view can be generated from existing data by arbitrary view generator 102.
  • Arbitrary view generator 102 generates and outputs the requested arbitrary view 108 in response to input arbitrary view request 104.
  • the resolution or quality of the generated arbitrary view 108 is the same as or similar to the qualities of the existing views used to generate it since pixels from those views are used to generate the arbitrary view.
  • the generated arbitrary view 108 is stored in database 106 with other existing views of the associated scene and may subsequently be employed to generate other arbitrary views of the scene in response to future requests for arbitrary views.
  • input 104 comprises a request for an existing view in database 106
  • the requested view does not need to be generated from other views as described; instead, the requested view is retrieved via a simple database lookup and directly presented as output 108.
  • Arbitrary view generator 102 may furthermore be configured to generate an arbitrary ensemble view using the described techniques. That is, input 104 may comprise a request to combine a plurality of objects into a single custom view. In such cases, the aforementioned techniques are performed for each of the plurality of objects and combined to generate a single consolidated or ensemble view comprising the plurality of objects. Specifically, existing views of each of the plurality of objects are selected and retrieved from database 106 by asset management engine 110, the existing views are transformed into the perspective of the requested view by perspective transformation engine 112, pixels from the perspective-transformed existing views are used to populate corresponding pixels of the requested ensemble view by merging engine 114, and any remaining unpopulated pixels in the ensemble view are interpolated by interpolation engine 116.
  • the requested ensemble view may comprise a perspective that already exists for one or more objects comprising the ensemble.
  • the existing view of an object asset corresponding to the requested perspective is employed to directly populate pixels corresponding to the object in the ensemble view instead of first generating the requested perspective from other existing views of the object.
  • each existing view As an example of an arbitrary ensemble view comprising a plurality of objects, consider the chair object of Figure 2 and an independently photographed or rendered table object.
  • the chair object and the table object may be combined using the disclosed techniques to generate a single ensemble view of both objects.
  • independently captured or rendered images or views of each of a plurality of objects can be consistently combined to generate a scene comprising the plurality of objects and having a desired perspective.
  • depth information of each existing view is known.
  • the perspective transformation of each existing view includes a depth transformation, allowing the plurality of objects to be appropriately positioned relative to one another in the ensemble view.
  • Generating an arbitrary ensemble view is not limited to combining a plurality of single objects into a custom view. Rather, a plurality of scenes having multiple objects or a plurality of rich virtual environments may be similarly combined into a custom ensemble view. For example, a plurality of separately and independently generated virtual environments, possibly from different content generation sources and possibly having different existing individual perspectives, may be combined into an ensemble view having a desired perspective.
  • arbitrary view generator 102 may be configured to consistently combine or reconcile a plurality of independent assets comprising possibly different existing views into an ensemble view having a desired, possibly arbitrary perspective. A perfectly harmonious resulting ensemble view is generated since all combined assets are normalized to the same perspective.
  • the possible arbitrary perspectives of the ensemble view may be constrained based on the existing views of the individual assets available to generate the ensemble view.
  • FIG. 3 is a flow chart illustrating an embodiment of a process for generating an arbitrary perspective.
  • Process 300 may be employed, for example, by arbitrary view generator 102 of Figure 1.
  • process 300 may be employed to generate an arbitrary view of a prescribed asset or an arbitrary ensemble view.
  • Process 300 starts at step 302 at which a request for an arbitrary perspective is received.
  • the request received at step 302 may comprise a request for an arbitrary perspective of a prescribed scene that is different from any existing available perspectives of the scene.
  • the arbitrary perspective request may be received in response to a requested change in perspective of a presented view of the scene.
  • Such a change in perspective may be facilitated by changing or manipulating a virtual camera associated with the scene, such as by panning the camera, changing the focal length, changing the zoom level, etc.
  • the request received at step 302 may comprise a request for an arbitrary ensemble view.
  • such an arbitrary ensemble view request may be received with respect to an application that allows a plurality of independent objects to be selected and provides a consolidated, perspective- corrected ensemble view of the selected objects.
  • a plurality of existing images from which to generate at least a portion of the requested arbitrary perspective is retrieved from one or more associated assets databases.
  • the plurality of retrieved images may be associated with a prescribed asset in the cases in which the request received at step 302 comprises a request for an arbitrary perspective of a prescribed asset or may be associated with a plurality of assets in the cases in which the request received at step 302 comprises a request for an arbitrary ensemble view.
  • each of the plurality of existing images retrieved at step 304 that has a different perspective is transformed into the arbitrary perspective requested at step 302.
  • Each of the existing images retrieved at step 304 includes associated perspective information.
  • step 306 comprises a simple mathematical operation.
  • step 306 also optionally includes a lighting transformation so that all images are consistently normalized to the same desired lighting conditions.
  • step 310 it is determined whether the generated image having the requested arbitrary perspective is complete. If it is determined at step 310 that the generated image having the requested arbitrary perspective is not complete, it is determined at step 312 whether any more existing images are available from which any remaining unpopulated pixels of the generated image may be mined. If it is determined at step 312 that more existing images are available, one or more additional existing images are retrieved at step 314, and process 300 continues at step 306.
  • any remaining unpopulated pixels of the generated image are interpolated at step 316. Any one or more appropriate interpolation techniques may be employed at step 316.
  • step 310 If it is determined at step 310 that the generated image having the requested arbitrary perspective is complete or after interpolating any remaining unpopulated pixels at step 316, the generated image having the requested arbitrary perspective is output at step 318. Process 300 subsequently ends.
  • the disclosed techniques may be used to generate an arbitrary perspective based on other existing perspectives. Normalizing different existing perspectives into a common, desired perspective is possible since camera information is preserved with each existing perspective. A resulting image having the desired perspective can be constructed from mining pixels from perspective-transformed existing images.
  • the processing associated with generating an arbitrary perspective using the disclosed techniques is not only fast and nearly instantaneous but also results in a high quality output, making the disclosed techniques particularly powerful for interactive, real-time graphics applications.
  • the disclosed techniques furthermore describe the generation of an arbitrary ensemble view comprising a plurality of objects by using available images or views of each of the plurality of objects.
  • perspective transformation and/or normalization allow pixels comprising independently captured or rendered images or views of the plurality of objects to be consistently combined into a desired arbitrary ensemble view.
  • a plurality of objects may be stacked or combined like building blocks to create a composite object comprising a scene or ensemble view.
  • the interactive application for instance, may comprise a visualization or modeling application.
  • Orthographic views of objects are in some embodiments employed to model or define a scene or ensemble view comprising a plurality of independent objects.
  • An orthographic view comprises a parallel projection that is approximated by a (virtual) camera positioned at a large distance relative to its size from the subject of interest and having a relatively long focal length so that rays or projection lines are substantially parallel.
  • Orthographic views comprise no or fixed depths and hence no or little perspective distortions.
  • orthographic views of objects may be employed similarly to building blocks when specifying an ensemble scene or a composite object. After an ensemble scene comprising an arbitrary combination of objects is specified or defined using such orthographic views, the scene or objects thereof may be transformed into any desired camera perspective using the arbitrary view generation techniques previously described with respect to the description of Figures 1-3.
  • the plurality of views of an asset stored in database 106 of system 100 of Figure 1 includes one or more orthographic views of the asset.
  • Such orthographic views may be captured (e.g., photographed or scanned) or rendered from a three-dimensional polygon mesh model.
  • an orthographic view may be generated from other views of an asset available in database 106 according to the arbitrary view generation techniques described with respect to the description of Figures 1-3.
  • Figures 4A-4N illustrate examples of an embodiment of an application in which independent objects are combined to generate an ensemble or composite object or scene. Specifically, Figures 4A-4N illustrate an example of a furniture building application in which various independent seating components are combined to generate different sectional configurations.
  • Figure 4A illustrates an example of perspective views of three independent seating components - a left-arm chair, an armless loveseat, and a right-arm chaise.
  • the perspective views in the example of Figure 4A each have a focal length of 25 mm.
  • the resulting perspective distortions prevent stacking of the components next to each other, i.e., side-by-side placement of the components, which may be desired when building a sectional configuration comprising the components.
  • Figure 4B illustrates an example of orthographic views of the same three components of Figure 4A.
  • the orthographic views of the objects are modular or block-like and amenable to being stacked or placed side-by-side.
  • depth information is substantially lost in the orthographic views.
  • all three components appear to have the same depth in the orthographic views despite the actual differences in depth that are visible in Figure 4A, especially with respect to the chaise.
  • Figure 4C illustrates an example of combining the orthographic views of the three components of Figure 4B to specify a composite object. That is, Figure 4C shows the generation of an orthographic view of a sectional via side-by-side placement of the orthographic views of the three components of Figure 4B. As depicted in Figure 4C, the bounding boxes of the orthographic views of the three seating components fit perfectly next to each other to create the orthographic view of the sectional. That is, the orthographic views of the components facilitate user friendly manipulations of the components in a scene as well as accurate placement.
  • Figures 4D and 4E each illustrate an example of transforming the orthographic view of the composite object of Figure 4C to an arbitrary camera perspective using the arbitrary view generation techniques previously described with respect to the description of Figures 1-3. That is, the orthographic view of the composite object is transformed into a normal camera perspective that accurately portrays depth in each of the examples of Figures 4D and 4E. As depicted, the relative depth of the chaise with respect to the chair and loveseat that was lost in the orthographic views is visible in the perspective views of Figures 4D and 4E.
  • Figures 4F, 4G, and 4H illustrate examples of a plurality of orthographic views of the left-arm chair, armless loveseat, and right-arm chaise, respectively.
  • any number of different views or perspectives of an asset may be stored in database 106 of system 100 of Figure 1.
  • the sets of Figures 4F-4H include twenty-five orthographic views corresponding to different angles around each asset that are independently captured or rendered and stored in database 106 and from which any arbitrary view of any combination of objects may be generated.
  • the top views may be useful for ground placement while the front views may be useful for wall placement.
  • only a prescribed number of orthographic views are stored for an asset in database 106 from which any arbitrary view of the asset may be generated.
  • Figures 4I-4N illustrate various examples of generating arbitrary views or perspectives of arbitrary combinations of objects. Specifically, each of Figures 4I-4N illustrates generating an arbitrary perspective or view of a sectional comprising a plurality of independent seating objects or components. Each arbitrary view may be generated, for example, by transforming one or more orthographic (or other) views of the objects comprising an ensemble view or composite object to the arbitrary view and harvesting pixels to populate the arbitrary view and possibly interpolating any remaining missing pixels using the arbitrary view generation techniques previously described with respect to the description of Figures 1-3. [0048] As previously described, each image or view of an asset in database 106 may be stored with corresponding metadata such as relative object and camera location and orientation information as well as lighting information. Metadata may be generated when rendering a view from a three-dimensional polygon mesh model of an asset, when imaging or scanning the asset (in which case depth and/or surface normal data may be estimated), or a combination of both.
  • Metadata may be generated when rendering a view from a three-
  • a prescribed view or image of an asset comprises pixel intensity values (e.g.,
  • RGB values for each pixel comprising the image as well as various metadata parameters associated with each pixel.
  • one or more of the red, green, and blue (RGB) channels or values of a pixel may be employed to encode the pixel metadata.
  • the pixel metadata may include information about the relative location or position (e.g., x, y, and z coordinate values) of the point in three-dimensional space that projects at that pixel.
  • the pixel metadata may include information about surface normal vectors (e.g., angles made with the x, y, and z axes) at that position.
  • the pixel metadata may include texture mapping coordinates (e.g., u and v coordinate values). In such cases, an actual pixel value at a point is determined by reading the RGB values at the corresponding coordinates in a texture image.
  • the surface normal vectors facilitate modifying or varying the lighting of a generated arbitrary view or scene. More specifically, re-lighting a scene comprises scaling pixel values based on how well the surface normal vectors of the pixels match the direction of a newly added, removed, or otherwise altered light source, which may at least in part be quantified, for example, by the dot product of the light direction and normal vectors of the pixels. Specifying pixel values via texture mapping coordinates facilitates modifying or varying the texture of a generated arbitrary view or scene or part thereof. More specifically, the texture can be changed by simply swapping or replacing a referenced texture image with another texture image having the same dimensions.
  • the disclosed arbitrary view generation techniques are effectively based on relatively low computational cost perspective transformations and/or lookup operations.
  • An arbitrary (ensemble) view may be generated by simply selecting the correct pixels and appropriately populating the arbitrary view being generated with those pixels.
  • pixel values may optionally be scaled, e.g., if lighting is being adjusted.
  • the low storage and processing overhead of the disclosed techniques facilitate fast, real-time or on-demand generation of arbitrary views of complex scenes that are of comparable quality to the high definition reference views from which they are generated.
  • assembling an ensemble or composite object or scene in some embodiments includes specifying a plurality of objects or assets comprising the ensemble using orthographic views.
  • Orthographic views facilitate accurate placements and alignments of the plurality of objects or assets in the ensemble scene.
  • An orthographic view of the ensemble scene may then be transformed into any arbitrary camera perspective to generate, for example, any desired or requested perspective.
  • Transforming the ensemble view into a prescribed camera perspective may comprise individually transforming each of the plurality of objects or assets comprising the ensemble scene into the prescribed perspective using the previously described techniques.
  • further improvements in efficiency may at least in part be facilitated by eliminating the processing associated with transforming (e.g., an orthographic or other view of) most of the plurality of objects or assets comprising an ensemble scene into a prescribed arbitrary perspective.
  • an available existing view of an object or asset that is closest or nearest to the prescribed arbitrary perspective for a prescribed position and orientation of that object or asset in the ensemble scene is employed for that object or asset when generating an output ensemble view or image that represents the prescribed arbitrary perspective.
  • the resulting output ensemble view is not completely perspective correct but provides a suitable approximation that is acceptable for many applications and is generated with significantly less latency relative to generating a completely perspective correct output.
  • Generating such an approximation of an arbitrary ensemble view for an arbitrary camera pose by employing a maximally quantized subset of already existing reference views of one or more objects or assets comprising the ensemble is next described in further detail.
  • Figure 5 is a high level flow chart illustrating an embodiment of a process for generating an arbitrary ensemble view.
  • process 500 is employed to efficiently generate an output image of an ensemble scene based at least in part on appropriately combining or compositing a single best matching existing view of at least one or more, if not most or all, objects or assets comprising the ensemble scene.
  • Process 500 starts at step 502 at which a request for a prescribed perspective of an ensemble scene is received.
  • the requested prescribed perspective of the ensemble scene comprises a selected or otherwise specified camera perspective or pose with respect to the ensemble scene and generally may comprise any arbitrary view.
  • An arbitrary view in the given context comprises any desired view or perspective of a scene whose specification or camera pose is not known in advance prior to being requested.
  • An ensemble scene comprises a combined view of a plurality of independent objects or assets.
  • a specification of an independent object or asset comprises a set of existing reference images or views of the individual object or asset having different camera perspectives and corresponding metadata, one or more of which may be used to generate or specify a portion of the ensemble scene associated with that object or asset.
  • the request of step 502 is received from an interactive mobile or web-based application that facilitates manipulation of camera angle or pose in an ensemble scene space and/or placement of a plurality of objects or assets to create a composite or ensemble scene.
  • the request may be received from a visualization or modeling application or an augmented reality (AR) application.
  • the request of step 502 is received with respect to an orthographic view of the ensemble scene since orthographic views facilitate easier manipulation, placement, and alignment of a plurality of objects or assets that comprise the ensemble scene.
  • a nearest or closest matching existing reference image or view is selected for each of at least a subset of one or more objects or assets comprising the ensemble scene.
  • Step 504 may be performed serially and/or in parallel for individual or independent objects or assets comprising the ensemble scene.
  • only one or a single existing reference image or view is selected for an object or asset that best matches the requested prescribed perspective for a given pose of that object or asset in the ensemble scene space.
  • the ensemble scene space comprises an ensemble scene coordinate system with a prescribed origin defined in an appropriate manner such as at the center (e.g., center of mass) of the ensemble scene.
  • the position and orientation or pose of that object or asset with respect to the ensemble scene coordinate system is determined and then translated or converted or otherwise correlated to an equivalent pose in its individual coordinate system that is associated with the existing reference images or views of that object or asset.
  • a simple camera metrics calculation having a relatively low computational complexity is performed based on the requested perspective and relative object or asset pose in the ensemble scene so that a closest matching existing reference image or view can be selected at step 504.
  • One or more criteria and/or thresholds may be defined to determine or identify the closest matching existing reference image or view for an object or asset.
  • an existing reference image or view is selected at step 504 only if one or more such thresholds are satisfied. In an ideal case, an exact match is found and selected at step 504.
  • one or more selection criteria and/or thresholds may not be satisfied if an available existing reference image dataset is too incomplete, such as when the available existing reference images or views of an object or asset are appreciably different from the requested perspective or if no reference images or views are available for the object or asset.
  • a closest matching placeholder or ghost image or view of the object or asset is instead selected at step 504.
  • Such a placeholder image or view represents the shape of the object or asset but lacks other attributes such as texture and optical properties.
  • a set of placeholder images that spans a sufficiently dense set of possible views around an object or asset e.g., that includes angles covering 360 degrees around the object or asset
  • Placeholders are then employed when fully rendered versions of an object or asset are unavailable or exhibit unacceptable deviations from the requested perspective.
  • an output image of the ensemble scene is generated for the requested prescribed perspective at least in part by appropriately combining or compositing the closest matching existing reference images or views of objects or assets comprising the ensemble scene that were selected at step 504.
  • Step 506 may include appropriately scaling or resizing a closest matching existing reference image or view selected for an object or asset and/or determining a location or position in the ensemble view at which to paste or composite the closest matching existing reference image or view selected for the object or asset.
  • the generated output image of the ensemble scene closely approximates the requested prescribed perspective. Since most objects or assets comprising the ensemble scene are represented in the output image with their nearest or closest available existing poses, these objects or assets are not completely perspective correct because they are not rigorously rendered or generated.
  • these objects or assets do not have the requested prescribed perspective in the output image unless an exact match is found in the available existing images or views.
  • the vanishing points of such objects or assets do not all converge at the same point in the output image, but the objects or assets are offset or skewed by an amount that in most cases is small enough (e.g., a few degrees) to trick the human visual system into perceiving the output image as perspective correct for the most part.
  • Consistency in the output image of the ensemble scene is furthermore facilitated by generating at least some portions of the ensemble scene in a globally consistent or similar manner, which further facilitates human interpretation of the output image as substantially visually accurate.
  • one or more objects or assets comprising the ensemble scene and/or (flat or other) surfaces, structural elements, global features, etc., comprising the ensemble scene may be rendered or generated rigorously to be correct in perspective, i.e., to have the requested prescribed perspective and not an approximation of the requested perspective.
  • the ensemble scene comprises a space such as a room
  • the walls, ceiling, floor, rugs, wall hangings, etc. may be generated using the camera pose of the requested perspective and thus may accurately be represented in the output image of the ensemble scene generated at step 506.
  • the output image of the ensemble scene may comprise a global lighting location that affects all portions of the scene in a similar and consistent manner, e.g., when relighting using available metadata such as surface normal vectors.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Graphics (AREA)
  • Computer Hardware Design (AREA)
  • Architecture (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Geometry (AREA)
  • Processing Or Creating Images (AREA)
  • Image Generation (AREA)

Abstract

La présente divulgation concerne des techniques permettant de générer une vue ou perspective arbitraire d'une scène d'ensemble. Selon certains modes de réalisation, en réponse à une demande reçue pour une perspective prescrite d'une scène d'ensemble comprenant une pluralité de ressources, une image de sortie de la scène d'ensemble selon la perspective prescrite demandée est générée sur la base, au moins en partie, de la combinaison d'au moins une partie d'une image existante de chacun d'au moins un sous-ensemble de la pluralité de ressources.
PCT/US2020/059188 2019-11-08 2020-11-05 Génération de vue arbitraire WO2021092229A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
KR1020227015247A KR20220076514A (ko) 2019-11-08 2020-11-05 임의적 뷰 생성
EP20884704.6A EP4055567A4 (fr) 2019-11-08 2020-11-05 Génération de vue arbitraire
JP2022525977A JP2022553844A (ja) 2019-11-08 2020-11-05 任意ビューの生成

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201962933254P 2019-11-08 2019-11-08
US62/933,254 2019-11-08
US17/089,597 2020-11-04
US17/089,597 US11972522B2 (en) 2016-03-25 2020-11-04 Arbitrary view generation

Publications (1)

Publication Number Publication Date
WO2021092229A1 true WO2021092229A1 (fr) 2021-05-14

Family

ID=75848737

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2020/059188 WO2021092229A1 (fr) 2019-11-08 2020-11-05 Génération de vue arbitraire

Country Status (4)

Country Link
EP (1) EP4055567A4 (fr)
JP (1) JP2022553844A (fr)
KR (1) KR20220076514A (fr)
WO (1) WO2021092229A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050018045A1 (en) * 2003-03-14 2005-01-27 Thomas Graham Alexander Video processing
US20130259448A1 (en) * 2008-10-03 2013-10-03 3M Innovative Properties Company Systems and methods for optimizing a scene
US20140198182A1 (en) * 2011-09-29 2014-07-17 Dolby Laboratories Licensing Corporation Representation and Coding of Multi-View Images Using Tapestry Encoding
US20150169982A1 (en) * 2013-12-17 2015-06-18 Canon Kabushiki Kaisha Observer Preference Model
US20190080506A1 (en) * 2016-03-25 2019-03-14 Outward, Inc. Arbitrary view generation

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10163249B2 (en) * 2016-03-25 2018-12-25 Outward, Inc. Arbitrary view generation

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050018045A1 (en) * 2003-03-14 2005-01-27 Thomas Graham Alexander Video processing
US20130259448A1 (en) * 2008-10-03 2013-10-03 3M Innovative Properties Company Systems and methods for optimizing a scene
US20140198182A1 (en) * 2011-09-29 2014-07-17 Dolby Laboratories Licensing Corporation Representation and Coding of Multi-View Images Using Tapestry Encoding
US20150169982A1 (en) * 2013-12-17 2015-06-18 Canon Kabushiki Kaisha Observer Preference Model
US20190080506A1 (en) * 2016-03-25 2019-03-14 Outward, Inc. Arbitrary view generation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4055567A4 *

Also Published As

Publication number Publication date
EP4055567A4 (fr) 2023-12-06
KR20220076514A (ko) 2022-06-08
EP4055567A1 (fr) 2022-09-14
JP2022553844A (ja) 2022-12-26

Similar Documents

Publication Publication Date Title
US11875451B2 (en) Arbitrary view generation
US11544829B2 (en) Arbitrary view generation
US20210217225A1 (en) Arbitrary view generation
US11676332B2 (en) Arbitrary view generation
US11232627B2 (en) Arbitrary view generation
US20220084280A1 (en) Arbitrary view generation
US11972522B2 (en) Arbitrary view generation
US11989820B2 (en) Arbitrary view generation
US11989821B2 (en) Arbitrary view generation
EP4055567A1 (fr) Génération de vue arbitraire
US12002149B2 (en) Machine learning based image attribute determination
KR20220074959A (ko) 임의적 뷰 생성

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20884704

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 20227015247

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2022525977

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020884704

Country of ref document: EP

Effective date: 20220608