CN117635701A - Shoe model posture optimization method, device, equipment and storage medium - Google Patents
Shoe model posture optimization method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117635701A CN117635701A CN202210958599.4A CN202210958599A CN117635701A CN 117635701 A CN117635701 A CN 117635701A CN 202210958599 A CN202210958599 A CN 202210958599A CN 117635701 A CN117635701 A CN 117635701A
- Authority
- CN
- China
- Prior art keywords
- shoe model
- model
- plane
- shoe
- current
- 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.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000001131 transforming effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- 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
- G06T19/006—Mixed reality
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for optimizing the posture of a shoe model. The method comprises the following steps: acquiring an initial shoe model to be subjected to gesture optimization, moving the initial shoe model based on preset reference point position information and central point position information of the initial shoe model to obtain a first shoe model with a central point moving to a preset reference point, and determining sole plane position information corresponding to the first shoe model; and rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with the sole plane parallel to the first reference plane, and performing posture optimization on the second shoe model based on model overlapping information between the second shoe model and the symmetrical shoe model to determine a target shoe model corresponding to the preset standard posture. According to the technical scheme provided by the embodiment of the invention, the automatic optimization of the shoe model posture can be realized, and the optimization efficiency of the shoe model posture can be further improved.
Description
Technical Field
Embodiments of the present invention relate to computer technology, and in particular, to a method, an apparatus, a device, and a storage medium for optimizing a posture of a shoe model.
Background
With the rapid development of computer technology, the display mode of article information is increasingly abundant, for example, shoes can be displayed based on a three-dimensional shoe model, so that a user can view details of the shoes without dead angles, and also can view actual try-on effects of the shoes in an augmented reality AR (Augmented Reality) shoe try-on mode.
At present, shoes are usually scanned and rebuilt to generate a shoe model, and the generated shoe model is always in any angle. In order to make the shoe model more fit to the look and feel of the user during the display, the generated shoe model is usually manually subjected to posture adjustment and optimization so as to display the optimized shoe model in a standard posture.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
the manual optimization mode in the prior art is time-consuming and labor-consuming, and reduces the optimization efficiency of the shoe model posture.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for optimizing the posture of a shoe model, which are used for realizing automatic optimization of the posture of the shoe model and improving the optimization efficiency of the posture of the shoe model.
In a first aspect, an embodiment of the present invention provides a method for optimizing a posture of a shoe model, including:
Acquiring an initial shoe model to be subjected to posture optimization;
moving the initial shoe model based on the preset reference point position information and the central point position information of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point;
determining sole plane position information corresponding to the first shoe model;
rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with the sole plane parallel to the first reference plane;
and optimizing the posture of the second shoe model based on model overlapping information between the second shoe model and the symmetrical shoe model, and determining a target shoe model corresponding to the preset standard posture, wherein the symmetrical shoe model is a shoe model obtained by symmetry of the second shoe model about a second reference plane.
In a second aspect, an embodiment of the present invention further provides a posture optimization apparatus for a shoe model, including:
the initial shoe model acquisition module is used for acquiring an initial shoe model to be subjected to gesture optimization;
the initial shoe model moving module is used for moving the initial shoe model based on the preset reference point position information and the central point position information of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point;
The plane position information determining module is used for determining the plane position information of the sole corresponding to the first shoe model;
the sole plane rotating module is used for rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with a sole plane parallel to the first reference plane;
the target shoe model determining module is used for optimizing the gesture of the second shoe model based on model overlapping information between the second shoe model and the symmetrical shoe model, and determining a target shoe model corresponding to the preset standard gesture, wherein the symmetrical shoe model is a shoe model obtained by the second shoe model in a symmetrical mode about a second reference plane.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a method for pose optimization of a shoe model as provided by any embodiment of the present invention.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for optimizing the pose of a shoe model as provided by any embodiment of the present invention.
According to the technical scheme, the initial shoe model to be subjected to gesture optimization is obtained, the initial shoe model is moved based on the position information of the preset reference point and the position information of the central point of the initial shoe model, the first shoe model with the central point moved to the preset reference point is obtained, the sole plane position information corresponding to the first shoe model is determined, the first shoe model is rotated based on the sole plane position information and the first reference plane position information, the second shoe model with the sole plane parallel to the first reference plane can be obtained, gesture optimization is carried out on the second shoe model according to the model overlapping information between the second shoe model and the symmetrical shoe model, the target shoe model corresponding to the preset standard gesture is determined, automatic optimization of the shoe model gesture can be achieved, manual participation is not needed, errors of manual optimization are reduced, and meanwhile optimization efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for optimizing the pose of a shoe model according to an embodiment of the present invention;
FIG. 1 (a) is an example of a shoe model pose optimization process according to an embodiment of the present invention;
FIG. 2 is a flowchart of another method for optimizing the stance of a shoe model provided by an embodiment of the present invention;
FIG. 3 is a flowchart of another method for optimizing the stance of a shoe model provided by an embodiment of the present invention;
FIG. 4 is a schematic structural view of a posture optimization apparatus for a shoe model according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Fig. 1 is a flowchart of a method for optimizing the posture of a shoe model according to an embodiment of the present invention, where the present embodiment may be applied to performing posture optimization on a shoe model with any posture to obtain a shoe model with a standard posture. The method may be performed by a pose optimization device of the shoe model, which may be implemented in software and/or hardware, integrated in an electronic device. As shown in fig. 1, the method specifically includes the following steps:
S110, acquiring an initial shoe model to be subjected to posture optimization.
Wherein, the initial shoe model may refer to a three-dimensional shoe model in an initial pose, which may refer to any pose. The shoe model may be a shoe model constructed for any kind of shoe. For example, the shoe model may be a sports shoe model, a travel shoe model, a leisure shoe model, and the like.
Specifically, a shoe model generated by scanning and reconstructing the shoe can be used as an initial shoe model to be subjected to posture optimization. For example, the initial shoe model may be composed of n points, i.e., n vertices, located on the shoe surface, i.e., v= { V 0 ,v 1 ,…,v n-1 A three-dimensional position coordinate corresponding to the ith vertex is v i ＝(x i ,y i ,z i ) T 。
And S120, moving the initial shoe model based on the position information of the preset reference point and the position information of the central point of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point.
The preset reference point may refer to a center position point of the standard shoe model in a preset standard posture. For example, the preset reference point may be, but is not limited to, an origin O in a three-dimensional coordinate system, i.e., the preset reference point position information refers to three-dimensional position coordinates of the origin O. The preset reference point in this embodiment may be determined based on a preset standard posture. The center point position information of the initial shoe model may refer to three-dimensional position coordinates of the center point of the initial shoe model. The first shoe model may refer to a corresponding shoe model when the center point position information coincides with the origin position of the three-dimensional coordinate system, and may be obtained by moving the initial shoe model.
In this embodiment, the position information of the center point of the initial shoe model may be determined based on the three-dimensional position coordinates corresponding to each vertex in the initial shoe model, and the center point is translated to a preset reference point, so that the position information of the center point of the initial shoe model is overlapped with the position information of the preset reference point, and the overlapped initial shoe model is used as the first shoe model. It should be noted that, the transformation of the movement of the center point of the initial shoe model is to transform all the vertices on the initial shoe model to obtain the corresponding first shoe model.
For example, the center point position information v of the shoe model can be determined by the following formula c ：
Fig. 1 (a) gives an example of a shoe model posture optimization process. As shown in fig. 1, when the preset reference point is the origin O, moving the center point of the initial shoe model to the origin O to obtain a first initial shoe model, that is, moving and transforming all the vertex positions on the initial shoe model, and transforming all the vertices on the transformed initial shoe model, that is, the first shoe model, into: v (V) T ＝{v 0 -v c ,v 1 -v c ,…,v n-1 -v c }。
S130, determining sole plane position information corresponding to the first shoe model.
The sole plane position information may refer to a plane position where the sole in the first shoe model is located.
Specifically, the shoe model is irregularly shaped, but the plane of the sole is substantially distributed near one plane in the shoe model, so that the plane in the vertex of the first shoe model can be determined based on the RANSAC algorithm, thereby obtaining the sole plane position information. The sole plane position information is determined so that the sole posture of the first shoe model can be determined through the sole plane position information, so that the overall posture of the shoe model is optimized.
And S140, rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with the sole plane parallel to the first reference plane.
The first reference plane may refer to a plane on which the sole of the standard shoe model is located in a preset standard posture, and the specific position of the first reference plane may be determined based on the preset standard posture. For example, the first reference plane may be, but is not limited to, an xOz plane that is composed of an x-axis and a z-axis. The second shoe model may refer to a shoe model corresponding to the sole plane obtained by rotating the first shoe model when the sole plane is parallel to the first reference plane.
Specifically, rotation information may be determined according to the position information of the sole plane and the position information of the first reference plane, and the first shoe model is rotated according to the rotation information, so that the sole plane in the first shoe model is aligned parallel to the first reference plane, and the first shoe model aligned parallel to the first reference plane is determined as the second shoe model.
For example, as shown in fig. 1 (a), when the first reference plane is an xOz plane, rotation information required for parallel alignment of the sole plane with the xOz plane may be determined based on the obtained sole plane position information and xOz plane position information, and the first shoe model may be rotated based on the rotation information such that the sole plane of the second shoe model obtained after rotation is aligned parallel with the xOz plane.
And S150, performing posture optimization on the second shoe model based on model overlapping information between the second shoe model and the symmetrical shoe model, and determining a target shoe model corresponding to the preset standard posture, wherein the symmetrical shoe model is a shoe model obtained by symmetry of the second shoe model about a second reference plane.
The second reference plane may refer to a symmetry plane of the standard shoe model in a preset standard posture, and the specific position of the second reference plane may be determined based on the preset standard posture. For example, the second reference plane may be, but is not limited to, an xOy plane consisting of an x-axis and a y-axis. The symmetrical shoe model may refer to a shoe model obtained by symmetrically transforming the second shoe model with respect to the second reference plane. The model overlap information may refer to information of an overlapping portion of the second shoe model and the symmetric shoe model, which may be, but is not limited to, the size of the overlap volume between the second shoe model and the symmetric shoe model. The target shoe model may refer to a shoe model whose pose is optimized to a preset standard pose. The preset standard posture may be a standard posture of the shoe model set in advance based on the business requirement. It is noted that the preset reference point position information, the first reference plane information, and the second reference plane information are determined based on the preset standard posture, and when the preset standard posture is changed, the preset reference point position information, the first reference plane information, and the second reference plane information may also be changed. For example, the preset standard pose may be, but is not limited to: the center point of the shoe model is positioned at the origin O of the coordinate system, the toe points to the x axis, the shoe mouth points upwards to the y axis, and the shoe body points to the z axis. Aiming at the preset standard gesture, a preset reference point is a coordinate system origin O; the first reference plane is an xOz plane formed by an x axis and a z axis; the second reference plane is an xOy plane formed by an x axis and a y axis.
Specifically, after the second shoe model is determined, the second shoe model may be symmetrically transformed based on the second reference plane, and the symmetrically transformed shoe model may be used as the symmetrical shoe model. The overlapping part exists between the symmetrical shoe model and the second shoe model in the same coordinate system, the size of the model overlapping volume between the second shoe model and the symmetrical shoe model is determined, the second shoe model is rotated, the model overlapping volume between the second shoe model and the symmetrical shoe model is maximized, and when the model overlapping volume is maximized, the second shoe model at the moment is determined to be a target shoe model corresponding to the preset standard posture, so that automatic optimization of the shoe model posture is realized, manual participation is not needed, and the optimization accuracy is ensured.
For example, as shown in fig. 1 (a), when the second reference plane is an xOy plane composed of an x-axis and a y-axis, the second shoe model is symmetrically transformed based on the xOy plane to obtain a symmetrical shoe model. And (3) maximizing the model overlapping volume between the second shoe model and the symmetrical shoe model by rotating the second shoe model, and determining the posture corresponding to the current second shoe model as a preset standard posture when the overlapping volume is maximum, thereby completing the standardized optimization process of the shoe model posture.
According to the technical scheme, the initial shoe model to be subjected to gesture optimization is obtained, the initial shoe model is moved based on the position information of the preset reference point and the position information of the central point of the initial shoe model, the first shoe model with the central point moved to the preset reference point is obtained, and the sole plane corresponding to the first shoe model is determined by determining the position information of the sole plane corresponding to the first shoe model so as to conveniently optimize the gesture of the shoe model. And then, based on the sole plane position information and the first reference plane position information, the first shoe model is rotated to obtain a second shoe model with the sole plane parallel to the first reference plane, and then, according to model overlapping information between the second shoe model and the symmetrical shoe model, the second shoe model is subjected to gesture optimization to determine a target shoe model corresponding to a preset standard gesture, so that the automatic optimization of the gesture of the shoe model can be realized, the shoe model in any gesture is converted into the standard gesture without manual participation, the error of manual optimization is reduced, and meanwhile, the optimization efficiency is improved.
Based on the above technical solution, S140 may include: determining a rotation angle and a rotation axis based on the sole plane position information and the first reference plane position information; determining a rotation matrix based on the rotation angle and the rotation axis; and performing rotation transformation on the position information of each vertex of the first shoe model based on the rotation matrix to obtain a second shoe model with a sole plane parallel to the first reference plane.
In this embodiment, in order to facilitate optimizing the shoe model pose to the target shoe model, it is necessary to rotate the shoe model pose such that the sole plane is parallel to the first reference plane. The rotation angle and the rotation axis required for the sole plane of the first shoe model to rotate to the first reference plane may be determined based on the position information of the sole plane and the position information of the first reference plane. The rotation matrix can be obtained based on the rotation formula, the rotation angle and the rotation axis, and the position information of each vertex of the first shoe model is rotationally transformed according to the rotation matrix, so that the sole plane of the first shoe model is parallel to the first reference plane, and the first shoe model parallel to the first reference plane is determined as the second shoe model.
For example, if the obtained sole plane position information is the plane equation ax+by+cz+d=0, the normal vector corresponding to the sole plane position information is n 1 = (a, b, c); the normal vector of the first reference plane xOz plane is n 2 = (0, 1, 0), normal vector n 1 And normal vector n 2 The included angle θ, i.e., the rotation angle θ is:
the rotation axis r is:
the rotation matrix R is obtained according to the rondrign rotation formula:
by the rotation matrix, the position information of each vertex of the first shoe model is rotated, namely, the vertex of the first shoe model is converted into RV T The sole plane in the rotated first shoe model is made parallel to the first reference plane, so that the second shoe model is automatically obtained.
Fig. 2 is a flowchart of another method for optimizing the posture of a shoe model according to an embodiment of the present invention, where a specific process of determining the sole plane position information corresponding to the first shoe model is described in detail on the basis of the above embodiments. Wherein the explanation of the same or corresponding terms as those of the above embodiments is not repeated herein.
Referring to fig. 2, another method for optimizing the posture of a shoe model according to this embodiment specifically includes the following steps:
s210, acquiring an initial shoe model to be subjected to posture optimization.
S220, moving the initial shoe model based on the preset reference point position information and the central point position information of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point.
S230, selecting any three pieces of vertex position information of the first shoe model, and determining the current selected plane position information based on the selected three pieces of vertex position information.
Although the three-dimensional model of the shoe is irregularly shaped, the sole plane is substantially distributed near one plane in the three-dimensional model. Vertices may refer to various points in the footwear model, with the vertices in the sole plane being substantially distributed about a plane. The currently selected plane position information may refer to plane position information constructed from currently selected non-collinear three vertices in the shoe model.
Specifically, three vertexes which are not located on the same straight line are randomly selected in the first shoe model, and the position information of a current selected plane corresponding to the current selected plane formed by the three vertexes is calculated according to the position information of the three vertexes, namely, a plane equation ax+by+cz+d=0. It should be noted that the current selected plane position information dynamically changes with the difference of three vertices selected each time.
S240, determining the distance between each residual vertex and the current selected plane based on the selected residual vertex position information and the current selected plane position information, and determining the number of target vertices positioned in the current selected plane based on the distance.
The target vertex number may refer to the number of remaining vertices located in the current selected plane among all remaining vertices except the three vertices that are currently selected randomly.
Specifically, according to the determined position information of the currently selected plane, the distance between each remaining vertex except three vertices randomly selected in the first shoe model and the currently selected plane is calculated respectively, and whether each remaining vertex is located in the currently selected plane or not is detected based on the distance between each remaining vertex and the currently selected plane, so that the number of target vertices corresponding to the currently selected plane is obtained.
Optionally, "determining the number of target vertices located in the currently selected plane based on the distance" in S240 may include: and taking the number of the residual vertexes with the distance smaller than or equal to a preset threshold value as the number of the target vertexes positioned in the current selected plane. The preset threshold may be preset based on a maximum distance value in a plane, which is set by a service scene. Specifically, if the distance from a certain residual vertex to the current selected plane is smaller than or equal to the preset threshold, the residual vertex is indicated to be an inner point in the current selected plane, the residual vertex can be determined to be a target vertex at the moment, and the number of target vertices corresponding to the current selected plane can be counted in the same way.
S250, updating the current target plane based on the number of target vertexes in the current selected plane and the number of target vertexes in the current target plane, and returning to S230.
Wherein the current target plane may refer to a plane currently having the largest number of target vertices. The initial value of the current target plane is a plane determined based on the three vertices selected for the first time, i.e., the selected plane obtained at the time of the first iteration.
Specifically, during the first iteration, the current selected plane determined by the three vertexes selected for the first time may be directly determined as the current target plane, so that, during the subsequent iteration, the number of target vertexes in the current selected plane in each iteration is compared with the number of target vertexes in the current target plane, the current target plane is updated based on the comparison result, the current iteration operation is completed, and the operation of executing steps S230-S250 is performed based on the updated current target plane, so that the current target plane with the maximum number of target vertexes is obtained through the re-iteration based on the re-selected three vertexes.
Optionally, the updating the current target plane based on the number of target vertices in the current selected plane and the number of target vertices in the current target plane in S250 may include: if the number of the target vertexes in the current selected plane is larger than the number of the target vertexes in the current target plane, determining the current selected plane as the current target plane so as to update the current target plane.
Specifically, if the number of the target vertices in the current selected plane is greater than the number of the target vertices in the current target plane, updating the current target plane, namely determining the current selected plane as the current target plane; if the number of the target vertexes in the current selected plane is smaller than or equal to the number of the target vertexes in the current target plane, the current target plane is not required to be updated, namely the current target plane is kept unchanged.
And S260, if the preset detection stopping condition is met currently, taking the current target plane position information as sole plane position information corresponding to the first shoe model.
The preset detection stopping condition can be preset, and the detection stopping condition is performed on the plane of the sole. For example, the preset detection stop condition may be, but is not limited to: the iteration number reaches the preset iteration number, and/or the number of the target vertexes in the current target is greater than or equal to the preset number. The preset iteration times can be determined through an iteration algorithm. The iterative algorithm may include, but is not limited to, the ransac algorithm. For example: determining a current selected plane according to 3 vertexes selected randomly, wherein the probability that all the 3 vertexes are target vertexes is p 3 And the probability of at least one of the 3 vertexes being a non-target vertex is 1-p 3 . If N iterations are performed, each randomly selected vertex has a probability of having a non-target vertex of (1-p 3 ) N The probability of selecting the target vertex at least once is 1- (1-p) 3 ) N The probability is greater than or equal to q, 1- (1-p) 3 ) N And (3) not less than q, the preset iteration times N can be deduced as follows:
specifically, before returning to S230, it may be detected whether the preset detection stop condition is currently satisfied, and if it is detected that the preset detection stop condition is currently satisfied, the current target plane may be determined as the sole plane corresponding to the first shoe model, and the current target plane position information may be used as the sole plane position information corresponding to the first shoe model. If it is detected that the preset detection stopping condition is not met, the iterative detection may be continued by returning to the mode of executing the steps S230 to S250 based on the current target plane.
And S270, rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with the sole plane parallel to the first reference plane.
S280, performing gesture optimization on the second shoe model based on model overlapping information between the second shoe model and a symmetrical shoe model, and determining a target shoe model corresponding to a preset standard gesture, wherein the symmetrical shoe model is a shoe model obtained by symmetry of the second shoe model about a second reference plane.
According to the technical scheme, optional three vertex position information of the first shoe model is selected, and the current selected plane position information is determined based on the selected three vertex position information; determining the distance between each residual vertex and the current selected plane based on the selected residual vertex position information and the current selected plane position information, and determining the number of target vertices positioned in the current selected plane based on the distance; updating the current target plane based on the number of target vertices in the current selected plane and the number of target vertices in the current target plane, and returning to the step of executing any three vertex position information of the selected first shoe model. If the preset detection stopping condition is met currently, the current target plane position information is used as sole plane position information corresponding to the first shoe model, so that the sole plane position information can be accurately determined in a cyclic iteration mode, and the accuracy of shoe model posture optimization is further improved.
Fig. 3 is a flowchart of another method for optimizing the posture of a shoe model according to an embodiment of the present invention, and the specific process of optimizing the posture of a second shoe model is described in detail on the basis of the above embodiments. Wherein the explanation of the same or corresponding terms as those of the above embodiments is not repeated herein.
Referring to fig. 3, another method for optimizing the posture of a shoe model according to this embodiment specifically includes the following steps:
s310, acquiring an initial shoe model to be subjected to posture optimization.
S320, moving the initial shoe model based on the preset reference point position information and the central point position information of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point.
S330, determining sole plane position information corresponding to the first shoe model.
And S340, rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with the sole plane parallel to the first reference plane.
S350, taking the second shoe model as the current optimized shoe model.
In particular, the second shoe model that has been obtained may be used as an initial value for the current optimized shoe model during the cycle.
S360, symmetrically transforming the current optimized shoe model based on the second reference plane to obtain a current symmetrical shoe model corresponding to the current optimized shoe model, and determining model overlapping information between the current optimized shoe model and the current symmetrical shoe model.
Specifically, the current optimized shoe model may be subjected to symmetric transformation based on the second reference plane to obtain a current symmetric shoe model after symmetric transformation, and model overlapping information between the current optimized shoe model and the current symmetric shoe model may be determined based on vertex position information of the current optimized shoe model and vertex position information of the current symmetric shoe model, for example, the size of the model overlapping volume between the current optimized shoe model and the current symmetric shoe model may be directly determined.
Illustratively, "determining model overlap information between the current optimized shoe model and the current symmetric shoe model" in S360 may include: determining a vertex distance between each first vertex and a corresponding second vertex based on the respective first vertex position information in the current optimized shoe model and the respective second vertex position information in the current symmetric shoe model; and carrying out average processing on each vertex distance, and determining the average vertex distance between the current optimized shoe model and the current symmetrical shoe model.
The first vertex position information may refer to coordinate position information of each first vertex in the current optimized shoe model. The second vertex position information may refer to coordinate position information of each second vertex in the current optimized shoe model, that is, position information of the second vertex where the first vertex is symmetrical with respect to the second reference plane. The average vertex distance may refer to an average distance between each first vertex and each second vertex. The embodiment can use the average vertex distance as model overlapping information to indirectly measure the size of the model overlapping volume so as to reduce the complexity of volume calculation and further improve the gesture optimization efficiency. For example, if the average vertex distance is greater, the smaller the model overlap volume is indicated.
Specifically, according to the position information of each first vertex and the position information of the corresponding second vertex, the vertex distance between each first vertex and the corresponding second vertex is calculated, and average calculation processing is carried out on the vertex distances, so that the average vertex distance between the current optimized shoe model and the current symmetrical shoe model is obtained. For example: let the current optimized shoe model be M and the current symmetric shoe model about xOy plane be M s The average vertex distance d between the current optimized shoe model and the current symmetric shoe model may be determined by the following formula:
wherein v is i Representing the first vertex in the current optimized shoe model M,representing a current symmetric shoe model M s Is included in the first vertex of the first row.
And S370, rotating the current optimized shoe model based on the preset rotation mode and the preset rotation shaft, taking the rotated shoe model as the current optimized shoe model, and returning to S360.
The preset rotation mode may be a rotation mode set in advance based on service requirements. For example, the preset rotation method may include: the rotation is performed based on a fixed angle, a binary search rotation is performed for the rotation angle, or the rotation angle is dynamically determined based on an average vertex distance. Wherein the fixed angle may be set to 2 deg. so as to rotate once every 2 deg.. The rotation angle of the binary search type rotation is not fixed, the binary search type rotation can be rotated once based on a preset angle, the current optimized shoe model is determined to be positioned on the left side or the right side of the standard shoe model, and the next rotation angle is determined according to a determination result until the standard posture is reached. The dynamically determining the rotation angle based on the average vertex distance may be determining the currently selected angle at the current average vertex distance to rotate based on a mapping relationship between a preset average vertex distance and the rotation angle. For example, when the average vertex distance is large, the current optimized shoe model is rotated at a large angle, and when the average vertex distance is small, the current optimized shoe model is rotated at a small angle. The preset rotation axis may refer to a direction in which the welt of the shoe model of the preset standard posture is pointed. For example, the preset rotation axis may be, but is not limited to, the y-axis in a coordinate system.
Specifically, the current rotation angle is determined according to the preset rotation mode, the current optimized shoe model is rotated based on the current rotation angle and the preset rotation axis, the rotated shoe model is used as the current optimized shoe model, the current optimized shoe model is updated, and the step S360-S370 is executed based on the updated current optimized shoe model in a returning mode so as to rotate next time.
And S380, when the model overlapping volume between the current optimized shoe model and the current symmetrical shoe model is determined to be maximum based on the model overlapping information, determining the current optimized shoe model with the maximum overlapping volume as a target shoe model corresponding to the preset standard gesture.
Specifically, when the model overlapping information is the model overlapping volume, the model overlapping volume between the current optimized shoe model and the current symmetric shoe model after each rotation can be directly compared, and the larger the model overlapping volume is, the closer the gesture of the current optimized shoe model is to the predicted standard gesture, at this time, the current optimized shoe model with the largest model overlapping volume can be determined as the target shoe model corresponding to the preset standard gesture, so that the gesture optimization process of the shoe model is completed.
Illustratively, S380 may include: and determining the current optimized shoe model with the minimum average vertex distance as a target shoe model corresponding to the preset standard posture. Specifically, when the model overlapping volume is indirectly measured by using the average vertex distance, since the overlapping volume between the current optimized shoe model with the minimum average vertex distance and the symmetrical shoe model is the largest, the average vertex distance between the current optimized shoe model and the current symmetrical shoe model after each rotation can be compared, and the current optimized shoe model with the minimum average vertex distance is determined as the target shoe model corresponding to the preset standard gesture, so that the gesture optimization efficiency can be further improved.
According to the technical scheme of the embodiment, the second shoe model is used as the current optimized shoe model; symmetrically transforming the current optimized shoe model based on the second reference plane to obtain a current symmetrical shoe model corresponding to the current optimized shoe model, and determining model overlapping information between the current optimized shoe model and the current symmetrical shoe model; rotating the current optimized shoe model based on a preset rotation mode and a preset rotation axis, taking the rotated shoe model as the current optimized shoe model, and returning to execute the operation of symmetrically transforming the current optimized shoe model based on the second reference plane based on the updated current optimized shoe model; when the model overlapping volume between the current optimized shoe model and the current symmetric shoe model is determined to be the largest based on the model overlapping information, the current optimized shoe model with the largest overlapping volume is determined to be the target shoe model corresponding to the preset standard gesture, so that gesture optimization can be performed on the second shoe model more accurately in a repeated rotation mode for multiple times, and the accuracy of gesture optimization is further improved.
The following is an embodiment of a posture optimization apparatus for a shoe model provided by the embodiment of the present invention, which belongs to the same inventive concept as the posture optimization method for a shoe model of each of the above embodiments, and details of which are not described in detail in the embodiment of the posture optimization apparatus for a shoe model may refer to the embodiment of the posture optimization method for a shoe model of the above embodiment.
Fig. 4 is a schematic structural diagram of an attitude optimization device for a shoe model according to an embodiment of the present invention, where the embodiment may be applied to performing attitude optimization on a shoe model in any attitude to obtain a shoe model in a standard attitude. As shown in fig. 4, the apparatus specifically includes: an initial shoe model acquisition module 410, an initial shoe model movement module 420, a planar position information determination module 430, a sole planar rotation module 440, and a target shoe model determination module 450.
Wherein, the initial shoe model obtaining module 410 is configured to obtain an initial shoe model to be posture-optimized; an initial shoe model moving module 420, configured to move the initial shoe model based on preset reference point position information and center point position information of the initial shoe model, to obtain a first shoe model with a center point moved to a preset reference point; a plane position information determining module 430, configured to determine sole plane position information corresponding to the first shoe model; a sole plane rotation module 440 for rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model in which the sole plane is parallel to the first reference plane; the target shoe model determining module 450 is configured to optimize a pose of the second shoe model based on model overlapping information between the second shoe model and a symmetric shoe model, and determine a target shoe model corresponding to a preset standard pose, where the symmetric shoe model is a shoe model obtained by symmetric the second shoe model about a second reference plane.
According to the technical scheme, the initial shoe model to be subjected to gesture optimization is obtained, the initial shoe model is moved based on the position information of the preset reference point and the position information of the central point of the initial shoe model, the first shoe model with the central point moved to the preset reference point is obtained, the sole plane position information corresponding to the first shoe model is determined, the first shoe model is rotated based on the sole plane position information and the first reference plane position information, the second shoe model with the sole plane parallel to the first reference plane can be obtained, gesture optimization is carried out on the second shoe model according to the model overlapping information between the second shoe model and the symmetrical shoe model, the target shoe model corresponding to the preset standard gesture is determined, automatic optimization of the shoe model gesture can be achieved, manual participation is not needed, errors of manual optimization are reduced, and meanwhile optimization efficiency is improved.
Optionally, the preset standard posture is: the center point of the shoe model is positioned at the origin O of the coordinate system, the toe cap points to the x axis, the shoe opening points to the y axis upwards, and the shoe body points to the z axis; the preset reference point is a coordinate system origin O; the first reference plane is an xOz plane formed by an x axis and a z axis; the second reference plane is an xOy plane formed by an x axis and a y axis.
Optionally, the plane position information determining module 430 includes:
the current selected plane position information determining unit is used for selecting any three pieces of vertex position information of the first shoe model and determining the current selected plane position information based on the three pieces of vertex position information;
the target vertex number determining unit is used for determining the distance between each residual vertex and the current selected plane based on the selected residual vertex position information and the current selected plane position information, and determining the number of target vertices positioned in the current selected plane based on the distance;
the target plane updating unit is used for updating the current target plane based on the number of target vertexes in the current selected plane and the number of target vertexes in the current target plane, and returning to the step of executing the position information of any three vertexes of the first shoe model;
and the sole plane position information determining unit is used for taking the current target plane position information as sole plane position information corresponding to the first shoe model if the preset detection stopping condition is met currently.
Optionally, the target vertex number determining unit is specifically configured to: taking the number of the residual vertexes with the distance smaller than or equal to a preset threshold value as the number of the target vertexes positioned in the current selected plane;
The target plane updating unit is specifically configured to: if the number of the target vertexes in the current selected plane is larger than the number of the target vertexes in the current target plane, determining the current selected plane as the current target plane so as to update the current target plane.
Optionally, the sole plane rotation module 440 further includes:
a rotation information determining unit for determining a rotation angle and a rotation axis based on the sole plane position information and the first reference plane position information;
a rotation matrix determining unit configured to determine a rotation matrix based on the rotation angle and the rotation axis;
and the model rotating unit is used for carrying out rotation transformation on the position information of each vertex of the first shoe model based on the rotation matrix to obtain a second shoe model with a sole plane parallel to the first reference plane.
Optionally, the target shoe model determining module 450 further includes:
a current optimized shoe model unit for taking the second shoe model as a current optimized shoe model;
the current symmetrical shoe model determining unit is used for symmetrically transforming the current optimized shoe model based on the second reference plane to obtain a current symmetrical shoe model corresponding to the current optimized shoe model, and determining model overlapping information between the current optimized shoe model and the current symmetrical shoe model;
The current optimization shoe model determining unit is used for rotating the current optimization shoe model based on a preset rotation mode and a preset rotation axis, taking the rotated shoe model as the current optimization shoe model, and executing the operation of symmetrically transforming the current optimization shoe model based on the second reference plane based on the updated current optimization shoe model;
and the target shoe model determining unit is used for determining the current optimized shoe model with the largest overlapping volume as the target shoe model corresponding to the preset standard gesture when determining that the model overlapping volume between the current optimized shoe model and the current symmetrical shoe model is the largest based on the model overlapping information.
Optionally, the current symmetric shoe model determining unit is specifically configured to:
determining a vertex distance between each first vertex and a corresponding second vertex based on the respective first vertex position information in the current optimized shoe model and the respective second vertex position information in the current symmetric shoe model; carrying out average processing on the vertex distances, and determining the average vertex distance between the current optimized shoe model and the current symmetrical shoe model; the target shoe model determining unit is specifically used for: and determining the current optimized shoe model with the minimum average vertex distance as a target shoe model corresponding to a preset standard posture.
The posture optimization device for the shoe model provided by the embodiment of the invention can execute the posture optimization method for the shoe model provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the posture optimization method for the shoe model.
It should be noted that, in the embodiment of the above-mentioned posture optimization apparatus for a shoe model, each unit and module included are only divided according to the functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Fig. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 5, the electronic device 12 is in the form of a general purpose computing device. Components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.
Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard disk drive"). Although not shown in fig. 5, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the electronic device 12, and/or any devices (e.g., network card, modem, etc.) that enable the electronic device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 20. As shown in fig. 5, the network adapter 20 communicates with other modules of the electronic device 12 over the bus 18. It should be appreciated that although not shown in fig. 5, other hardware and/or software modules may be used in connection with electronic device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the posture optimization method steps of a shoe model provided by the embodiment of the present invention, the method includes:
acquiring an initial shoe model to be subjected to posture optimization;
moving the initial shoe model based on the preset reference point position information and the central point position information of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point;
determining sole plane position information corresponding to the first shoe model;
rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with the sole plane parallel to the first reference plane;
and optimizing the posture of the second shoe model based on model overlapping information between the second shoe model and the symmetrical shoe model, and determining a target shoe model corresponding to the preset standard posture, wherein the symmetrical shoe model is a shoe model obtained by symmetry of the second shoe model about a second reference plane.
Of course, those skilled in the art will appreciate that the processor may also implement the technical solution of the method for optimizing the posture of the shoe model provided in any embodiment of the present invention.
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the posture optimization method steps of a shoe model as provided by any of the embodiments of the present invention, the method comprising:
acquiring an initial shoe model to be subjected to posture optimization;
moving the initial shoe model based on the preset reference point position information and the central point position information of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point;
determining sole plane position information corresponding to the first shoe model;
rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with the sole plane parallel to the first reference plane;
and optimizing the posture of the second shoe model based on model overlapping information between the second shoe model and the symmetrical shoe model, and determining a target shoe model corresponding to the preset standard posture, wherein the symmetrical shoe model is a shoe model obtained by symmetry of the second shoe model about a second reference plane.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
It will be appreciated by those of ordinary skill in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed over a network of computing devices, or they may alternatively be implemented in program code executable by a computer device, such that they are stored in a memory device and executed by the computing device, or they may be separately fabricated as individual integrated circuit modules, or multiple modules or steps within them may be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (10)
1. A method for optimizing the pose of a shoe model, comprising:
acquiring an initial shoe model to be subjected to posture optimization;
moving the initial shoe model based on the position information of the preset reference point and the position information of the central point of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point;
determining sole plane position information corresponding to the first shoe model;
rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with a sole plane parallel to the first reference plane;
and optimizing the posture of the second shoe model based on model overlapping information between the second shoe model and a symmetrical shoe model, and determining a target shoe model corresponding to a preset standard posture, wherein the symmetrical shoe model is a shoe model obtained by symmetrical the second shoe model about a second reference plane.
2. The method according to claim 1, wherein the preset standard pose is: the center point of the shoe model is positioned at the origin O of the coordinate system, the toe cap points to the x axis, the shoe opening points to the y axis upwards, and the shoe body points to the z axis; the preset reference point is a coordinate system origin O; the first reference plane is an xOz plane formed by an x axis and a z axis; the second reference plane is an xOy plane formed by an x axis and a y axis.
3. The method of claim 1, wherein the determining sole plane position information corresponding to the first shoe model comprises:
selecting any three vertex position information of the first shoe model, and determining the current selected plane position information based on the selected three vertex position information;
determining the distance between each residual vertex and the current selected plane based on the selected residual vertex position information and the current selected plane position information, and determining the number of target vertices positioned in the current selected plane based on the distance;
updating the current target plane based on the number of target vertexes in the current selected plane and the number of target vertexes in the current target plane, and returning to the step of executing any three vertex position information of the first shoe model;
and if the preset detection stopping condition is met currently, taking the current target plane position information as sole plane position information corresponding to the first shoe model.
4. A method according to claim 3, wherein said determining the number of target vertices lying in the currently selected plane based on said distance comprises:
taking the number of the residual vertexes with the distance smaller than or equal to a preset threshold value as the number of the target vertexes positioned in the current selected plane;
The updating the current target plane based on the number of target vertices in the current selected plane and the number of target vertices in the current target plane comprises:
if the number of the target vertexes in the current selected plane is larger than the number of the target vertexes in the current target plane, determining the current selected plane as the current target plane so as to update the current target plane.
5. The method of claim 1, wherein rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model having a sole plane parallel to the first reference plane comprises:
determining a rotation angle and a rotation axis based on the sole plane position information and the first reference plane position information;
determining a rotation matrix based on the rotation angle and the rotation axis;
and carrying out rotation transformation on the position information of each vertex of the first shoe model based on the rotation matrix to obtain a second shoe model with a sole plane parallel to the first reference plane.
6. The method according to any one of claims 1-5, wherein the performing posture optimization on the second shoe model based on model overlapping information between the second shoe model and the symmetrical shoe model, determining a target shoe model corresponding to a preset standard posture, includes:
Taking the second shoe model as a current optimized shoe model;
symmetrically transforming the current optimized shoe model based on the second reference plane to obtain a current symmetrical shoe model corresponding to the current optimized shoe model, and determining model overlapping information between the current optimized shoe model and the current symmetrical shoe model;
rotating the current optimized shoe model based on a preset rotation mode and a preset rotation shaft, taking the rotated shoe model as the current optimized shoe model, and returning to execute the operation of symmetrically transforming the current optimized shoe model based on the second reference plane based on the updated current optimized shoe model;
and when the model overlapping information is based on that the model overlapping volume between the current optimized shoe model and the current symmetrical shoe model is maximum, determining the current optimized shoe model with the maximum overlapping volume as a target shoe model corresponding to the preset standard gesture.
7. The method of claim 6, wherein the determining model overlap information between the current optimized shoe model and the current symmetric shoe model comprises:
determining a vertex distance between each first vertex and a corresponding second vertex based on the respective first vertex position information in the current optimized shoe model and the respective second vertex position information in the current symmetric shoe model;
Carrying out average processing on the vertex distances, and determining the average vertex distance between the current optimized shoe model and the current symmetrical shoe model;
when determining that the model overlapping volume between the current optimized shoe model and the current symmetric shoe model is maximum based on the model overlapping information, determining the current optimized shoe model with the maximum overlapping volume as the target shoe model corresponding to the preset standard posture, including:
and determining the current optimized shoe model with the minimum average vertex distance as a target shoe model corresponding to a preset standard posture.
8. A posture optimization apparatus for a shoe model, comprising:
the initial shoe model acquisition module is used for acquiring an initial shoe model to be subjected to gesture optimization;
the initial shoe model moving module is used for moving the initial shoe model based on the preset reference point position information and the central point position information of the initial shoe model to obtain a first shoe model with the central point moving to the preset reference point;
the plane position information determining module is used for determining the plane position information of the sole corresponding to the first shoe model;
the sole plane rotating module is used for rotating the first shoe model based on the sole plane position information and the first reference plane position information to obtain a second shoe model with a sole plane parallel to the first reference plane;
The target shoe model determining module is used for optimizing the gesture of the second shoe model based on model overlapping information between the second shoe model and a symmetrical shoe model, and determining a target shoe model corresponding to a preset standard gesture, wherein the symmetrical shoe model is a shoe model obtained by symmetry of the second shoe model about a second reference plane.
9. An electronic device, the electronic device comprising:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of pose optimization for a shoe model according to any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements a method for optimizing the pose of a shoe model according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210958599.4A CN117635701A (en) | 2022-08-09 | 2022-08-09 | Shoe model posture optimization method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210958599.4A CN117635701A (en) | 2022-08-09 | 2022-08-09 | Shoe model posture optimization method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117635701A true CN117635701A (en) | 2024-03-01 |
Family
ID=90020404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210958599.4A Pending CN117635701A (en) | 2022-08-09 | 2022-08-09 | Shoe model posture optimization method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117635701A (en) |
-
2022
- 2022-08-09 CN CN202210958599.4A patent/CN117635701A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163903B (en) | Three-dimensional image acquisition and image positioning method, device, equipment and storage medium | |
| JP6966588B2 (en) | Intersection drawing methods, devices, servers and storage media | |
| CN110322500B (en) | Optimization method and device for instant positioning and map construction, medium and electronic equipment | |
| EP3872764B1 (en) | Method and apparatus for constructing map | |
| CN110222703B (en) | Image contour recognition method, device, equipment and medium | |
| CN109191554B (en) | Super-resolution image reconstruction method, device, terminal and storage medium | |
| TWI748409B (en) | Data processing method, processor, electronic device and computer readable medium | |
| CN109272442B (en) | Method, device and equipment for processing panoramic spherical image and storage medium | |
| CN110349212B (en) | Optimization method and device for instant positioning and map construction, medium and electronic equipment | |
| CN113409368B (en) | Mapping method and device, computer readable storage medium and electronic equipment | |
| US20210383241A1 (en) | Training neural networks with limited data using invertible augmentation operators | |
| CN114677572B (en) | Object description parameter generation method and deep learning model training method | |
| CN112733641B (en) | Object size measuring method, device, equipment and storage medium | |
| CN111368927A (en) | Method, device and equipment for processing labeling result and storage medium | |
| US20240078284A1 (en) | Two-way descriptor matching on deep learning accelerator | |
| CN114187589A (en) | Target detection method, device, equipment and storage medium | |
| WO2022121653A1 (en) | Transparency determination method and apparatus, electronic device, and storage medium | |
| US8270770B1 (en) | Region-based dense feature correspondence | |
| CN110096134B (en) | VR handle ray jitter correction method, device, terminal and medium | |
| US11836839B2 (en) | Method for generating animation figure, electronic device and storage medium | |
| CN112085842B (en) | Depth value determining method and device, electronic equipment and storage medium | |
| CN117635701A (en) | Shoe model posture optimization method, device, equipment and storage medium | |
| US20240193804A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN112528707A (en) | Image processing method, device, equipment and storage medium | |
| US20220155087A1 (en) | Map data processing method, device, storage medium and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |