Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Claims
Claims 1, 4, 5, 11, 14, 15, 17 are amended.
Claims 2, 3, 6-10, 12, 13, 16, 18-20 have been previously presented.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-4, 8-10, 11-14, 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu (Patent No. US 20180330480 A1) in view of Pang (NPL: Developing a Parametric 3D Face Model Editing Algorithm, 09/09/2020), in further view of Kang (Patent No. US 20220157020 A1).
Regarding claim 1 Liu teaches A computer-implemented method, comprising: (Liu, “[0087] One or more methods described herein may be implemented in computer programs executing on programmable computers, each comprising at least one processor, a data storage system (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device.”)
obtaining a source three-dimensional (3D) mesh of a face of an avatar, wherein the source 3D mesh includes a first plurality of polygons; (Liu, “[0092] The method may include dynamic receiving, capable of receiving 3D models from many file types. For example, as shown in FIG. 2, a computer-aided design (CAD) model 1011 may be revived from object files. The CAD model 1011 may include a set of mesh data, such as, for example, polygon mesh data or triangle mesh data.”)
generating a second 3D mesh based on the source 3D mesh, wherein a count of polygons in the second 3D mesh is fewer than a count of polygons in the source 3D mesh; (Liu, “[0147] The 3D artist uses the high-poly version of the 3D model as a base mesh to create a low-poly version of the 3D model through retopology. Retopology uses mesh reduction techniques, such as mesh decimation, to reduce the polygon count of the high-poly model.”)
determining a two-dimensional (2D) parameterization of the second 3D mesh; (Liu, “[0167] At 2020, the reduced 3D model is UV mapped to bring back the texture of the asset. “Baking” is a term often used in 3D modelling to describe a process of bringing in or applying texture to a surface. UV mapping is a process of projecting a 2D image to a 3D model's surface for the purposes of texture mapping.”)
However, Liu is silent about determining a target 2D parameterization based on a template 3D mesh and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; and reconstructing the target 2D parameterization into a target 3D mesh, wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh.
Pang teaches determining a target 2D parameterization based on a template 3D mesh (Pang, Pg. 167211 , “The proposed model editing algorithm begins with select ing from a 3D model database a number of face models wearing different expressions, one of them being defined as the source model, from which a set of characteristic points are extracted. The rest of the selected face models are used, one by one, as the target models”) and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; (Pang, Pg. 167211, “Third, based on previously selected characteristic point sets, corresponding point sets are sequentially extracted on the 2D planes of the source model and the target models; with these point sets, control points are established for model editing.”)
and reconstructing the target 2D parameterization into a target 3D mesh. (Pang, , “Finally, these generated 2D models are restored to 3D models, and this completes smooth transition of facial expressions.”)
wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; (Kang, “[0098] The online fitting apparatus may extract, from the obtained barycentric coordinate information, an index (e.g., index no. 14) of the first polygon 501 included in the first mesh forming the reference avatar, and a plurality of parameters representing a 3D position of a point 520 of the clothes matched to the first polygon 501 based on the first polygon 501. In addition to the index (e.g., index no. 14) of the first polygon 501, the online fitting apparatus may extract coefficients α and R for calculating the barycentric coordinate information, and an offset between a barycentric point 510 of the first polygon 501 and a point 520 of a second polygon of the clothes of the target size draped over the reference avatar. The first polygon 501 may not be a polygon of the clothes, but be a polygon (or a first polygon) of the reference avatar, and the point 520 may be one of points that constitute the polygon of the clothes. A polygon of the reference avatar that is closest to the point 520 constituting the polygon of the clothes may be the first polygon 501, and a point closest to the point 520 among points on the first polygon 501 may be the point 510.”)
and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh. (Kang, “[0133] For example, the processor 1050 may extract, from the barycentric coordinate information, an index of the first polygon included in the first mesh forming the reference avatar, and a plurality of parameters representing a 3D position of a point of the clothes matched to the first polygon based on the first polygon. The processor 1050 may identify a target polygon corresponding to the first polygon from a third mesh forming the target avatar based on the mesh topology and the index of the first polygon. The processor 1050 may determine the 3D position of the point of the clothes by applying the parameters to the target polygon. The 3D position of the point of the clothes determined by the processor 1050 may correspond to a result of fitting the clothes to the target avatar. / [0131] The communication interface 1030 may obtain barycentric coordinate information corresponding to a result of fitting the clothes of the target size to a reference avatar selected based on the body size of the user. The barycentric coordinate information may include at least one of parameters representing a 3D position transformation relationship between a first polygon of a first mesh forming the reference avatar and a point of a second polygon of a second mesh forming the clothes draped over the reference avatar, or an index of the second polygon. The parameters may include at least one of coefficients for calculating the barycentric coordinate information, or an offset between the first polygon and the point of the second polygon.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including determining a target 2D parameterization based on a template 3D mesh and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; and reconstructing the target 2D parameterization into a target 3D mesh, wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh as taught by Pang and Kang, and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve landmarks identification and reconstruction of 2D parameterization to 3D model, and to introduce barycentric coordinate to specify the location of the vertex inside the specific shape.
Regarding claim 11 teaches A non-transitory computer-readable medium with instructions stored thereon that, responsive to execution by a processing device, cause the processing device to perform operations comprising: (Liu, “[0087] One or more methods described herein may be implemented in computer programs executing on programmable computers, each comprising at least one processor, a data storage system (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. For example, and without limitation, the programmable computer may be a programmable logic unit, a mainframe computer, server, and personal computer, cloud based program or system, laptop, personal data assistance, cellular telephone, smartphone, or tablet device.”, “[0088] Each program is preferably implemented in a high level procedural or object oriented programming and/or scripting language to communicate with a computer system. However, the programs can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Each such computer program is preferably stored on a storage media or a device readable by a general or special purpose programmable computer for configuring and operating the computer when the storage media or device is read by the computer to perform the procedures described herein.”)
obtaining a source three-dimensional (3D) mesh of a face of an avatar, wherein the source 3D mesh includes a first plurality of polygons; (Liu, “[0092] The method may include dynamic receiving, capable of receiving 3D models from many file types. For example, as shown in FIG. 2, a computer-aided design (CAD) model 1011 may be revived from object files. The CAD model 1011 may include a set of mesh data, such as, for example, polygon mesh data or triangle mesh data.”)
generating a second 3D mesh based on the source 3D mesh, wherein a count of polygons in the second 3D mesh is fewer than a count of polygons in the source 3D mesh; (Liu, “[0147] The 3D artist uses the high-poly version of the 3D model as a base mesh to create a low-poly version of the 3D model through retopology. Retopology uses mesh reduction techniques, such as mesh decimation, to reduce the polygon count of the high-poly model.”)
determining a two-dimensional (2D) parameterization of the second 3D mesh; (Liu, “[0167] At 2020, the reduced 3D model is UV mapped to bring back the texture of the asset. “Baking” is a term often used in 3D modelling to describe a process of bringing in or applying texture to a surface. UV mapping is a process of projecting a 2D image to a 3D model's surface for the purposes of texture mapping.”)
However, Liu is silent about determining a target 2D parameterization based on a template 3D mesh and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; and reconstructing the target 2D parameterization into a target 3D mesh, wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh.
Pang teaches determining a target 2D parameterization based on a template 3D mesh (Pang, Pg. 167211 , “The proposed model editing algorithm begins with select ing from a 3D model database a number of face models wearing different expressions, one of them being defined as the source model, from which a set of characteristic points are extracted. The rest of the selected face models are used, one by one, as the target models”) and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; (Pang, Pg. 167211, “Third, based on previously selected characteristic point sets, corresponding point sets are sequentially extracted on the 2D planes of the source model and the target models; with these point sets, control points are established for model editing.”)
and reconstructing the target 2D parameterization into a target 3D mesh. (Pang, , “Finally, these generated 2D models are restored to 3D models, and this completes smooth transition of facial expressions.”)
wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; (Kang, “[0098] The online fitting apparatus may extract, from the obtained barycentric coordinate information, an index (e.g., index no. 14) of the first polygon 501 included in the first mesh forming the reference avatar, and a plurality of parameters representing a 3D position of a point 520 of the clothes matched to the first polygon 501 based on the first polygon 501. In addition to the index (e.g., index no. 14) of the first polygon 501, the online fitting apparatus may extract coefficients α and R for calculating the barycentric coordinate information, and an offset between a barycentric point 510 of the first polygon 501 and a point 520 of a second polygon of the clothes of the target size draped over the reference avatar. The first polygon 501 may not be a polygon of the clothes, but be a polygon (or a first polygon) of the reference avatar, and the point 520 may be one of points that constitute the polygon of the clothes. A polygon of the reference avatar that is closest to the point 520 constituting the polygon of the clothes may be the first polygon 501, and a point closest to the point 520 among points on the first polygon 501 may be the point 510.”)
and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh. (Kang, “[0133] For example, the processor 1050 may extract, from the barycentric coordinate information, an index of the first polygon included in the first mesh forming the reference avatar, and a plurality of parameters representing a 3D position of a point of the clothes matched to the first polygon based on the first polygon. The processor 1050 may identify a target polygon corresponding to the first polygon from a third mesh forming the target avatar based on the mesh topology and the index of the first polygon. The processor 1050 may determine the 3D position of the point of the clothes by applying the parameters to the target polygon. The 3D position of the point of the clothes determined by the processor 1050 may correspond to a result of fitting the clothes to the target avatar. / [0131] The communication interface 1030 may obtain barycentric coordinate information corresponding to a result of fitting the clothes of the target size to a reference avatar selected based on the body size of the user. The barycentric coordinate information may include at least one of parameters representing a 3D position transformation relationship between a first polygon of a first mesh forming the reference avatar and a point of a second polygon of a second mesh forming the clothes draped over the reference avatar, or an index of the second polygon. The parameters may include at least one of coefficients for calculating the barycentric coordinate information, or an offset between the first polygon and the point of the second polygon.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including determining a target 2D parameterization based on a template 3D mesh and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; and reconstructing the target 2D parameterization into a target 3D mesh, wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh as taught by Pang and Kang, and use that with Liu’s system and methods for generating and optimized 3D model.
Regarding claim 17 Liu teaches A system comprising: (Liu, “[0006] In accordance with an embodiment of the invention, there is provided a system for making an optimized three-dimensional (3D) model. The system includes: i) a processor for receiving a high-poly 3D model, wherein the processor is configured to: divide the high-poly 3D model into a plurality of subcomponents; approximate each subcomponent of the plurality of subcomponents by a geometric shape; adjust the geometric shape to conform to the subcomponent; merge the adjusted geometric shapes to form a reduced 3D model; and texture map the reduced 3D model to provide texture of the high-poly 3D model to form the optimized 3D model; ii) a memory connected to the processor for storing the high-poly 3D model and the optimized 3D model; and iii) a 3D model display for displaying the optimized 3D model.”)
obtaining a source three-dimensional (3D) mesh of a face of an avatar, wherein the source 3D mesh includes a first plurality of polygons; (Liu, “[0092] The method may include dynamic receiving, capable of receiving 3D models from many file types. For example, as shown in FIG. 2, a computer-aided design (CAD) model 1011 may be revived from object files. The CAD model 1011 may include a set of mesh data, such as, for example, polygon mesh data or triangle mesh data.”)
generating a second 3D mesh based on the source 3D mesh, wherein a count of polygons in the second 3D mesh is fewer than a count of polygons in the source 3D mesh; (Liu, “[0147] The 3D artist uses the high-poly version of the 3D model as a base mesh to create a low-poly version of the 3D model through retopology. Retopology uses mesh reduction techniques, such as mesh decimation, to reduce the polygon count of the high-poly model.”)
determining a two-dimensional (2D) parameterization of the second 3D mesh; (Liu, “[0167] At 2020, the reduced 3D model is UV mapped to bring back the texture of the asset. “Baking” is a term often used in 3D modelling to describe a process of bringing in or applying texture to a surface. UV mapping is a process of projecting a 2D image to a 3D model's surface for the purposes of texture mapping.”)
However, Liu is silent about determining a target 2D parameterization based on a template 3D mesh and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; and reconstructing the target 2D parameterization into a target 3D mesh, wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh.
Pang teaches determining a target 2D parameterization based on a template 3D mesh (Pang, Pg. 167211 , “The proposed model editing algorithm begins with select ing from a 3D model database a number of face models wearing different expressions, one of them being defined as the source model, from which a set of characteristic points are extracted. The rest of the selected face models are used, one by one, as the target models”) and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; (Pang, Pg. 167211, “Third, based on previously selected characteristic point sets, corresponding point sets are sequentially extracted on the 2D planes of the source model and the target models; with these point sets, control points are established for model editing.”)
and reconstructing the target 2D parameterization into a target 3D mesh. (Pang, , “Finally, these generated 2D models are restored to 3D models, and this completes smooth transition of facial expressions.”)
wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; (Kang, “[0098] The online fitting apparatus may extract, from the obtained barycentric coordinate information, an index (e.g., index no. 14) of the first polygon 501 included in the first mesh forming the reference avatar, and a plurality of parameters representing a 3D position of a point 520 of the clothes matched to the first polygon 501 based on the first polygon 501. In addition to the index (e.g., index no. 14) of the first polygon 501, the online fitting apparatus may extract coefficients α and R for calculating the barycentric coordinate information, and an offset between a barycentric point 510 of the first polygon 501 and a point 520 of a second polygon of the clothes of the target size draped over the reference avatar. The first polygon 501 may not be a polygon of the clothes, but be a polygon (or a first polygon) of the reference avatar, and the point 520 may be one of points that constitute the polygon of the clothes. A polygon of the reference avatar that is closest to the point 520 constituting the polygon of the clothes may be the first polygon 501, and a point closest to the point 520 among points on the first polygon 501 may be the point 510.”)
and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh. (Kang, “[0133] For example, the processor 1050 may extract, from the barycentric coordinate information, an index of the first polygon included in the first mesh forming the reference avatar, and a plurality of parameters representing a 3D position of a point of the clothes matched to the first polygon based on the first polygon. The processor 1050 may identify a target polygon corresponding to the first polygon from a third mesh forming the target avatar based on the mesh topology and the index of the first polygon. The processor 1050 may determine the 3D position of the point of the clothes by applying the parameters to the target polygon. The 3D position of the point of the clothes determined by the processor 1050 may correspond to a result of fitting the clothes to the target avatar. / [0131] The communication interface 1030 may obtain barycentric coordinate information corresponding to a result of fitting the clothes of the target size to a reference avatar selected based on the body size of the user. The barycentric coordinate information may include at least one of parameters representing a 3D position transformation relationship between a first polygon of a first mesh forming the reference avatar and a point of a second polygon of a second mesh forming the clothes draped over the reference avatar, or an index of the second polygon. The parameters may include at least one of coefficients for calculating the barycentric coordinate information, or an offset between the first polygon and the point of the second polygon.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including determining a target 2D parameterization based on a template 3D mesh and the 2D parameterization of the second 3D mesh such that one or more landmarks identified in the source 3D mesh are aligned with corresponding landmarks on the template 3D mesh; and reconstructing the target 2D parameterization into a target 3D mesh, wherein reconstructing the target 2D parameterization comprises: computing barycentric coordinates of a 2D position of a vertex of the target 2D parameterization based on the template 3D mesh with respect to a triangle of the 2D parameterization of the second 3D mesh; and determining a 3D position of the vertex in the target 3D mesh by evaluating the barycentric coordinates of the 2D position of the vertex on a triangle of the second 3D mesh that corresponds to the triangle of the 2D parameterization of the second 3D mesh as taught by Pang and Kang, and use that with Liu’s system and methods for generating and optimized 3D model.
Regarding claim 2 and 12 Liu is silent about wherein generating the second 3D mesh comprises obtaining a trimmed 3D mesh by excluding particular portions of the source 3D mesh.
Pang teaches wherein generating the second 3D mesh comprises obtaining a trimmed 3D mesh by excluding particular portions of the source 3D mesh. (Pang, Pg. 167210, “Patel et al. [16] propose to use the features extracted from a given frontal facial image and transform an existing face model through geometric transformation.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including wherein generating the second 3D mesh comprises obtaining a trimmed 3D mesh by excluding particular portions of the source 3D mesh as taught by Pang and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve trimming or transformation of model.
Regarding claim 3 and 13 Liu is silent about wherein the particular portions of the source 3D mesh are one or more of: portions of the source 3D mesh that correspond to hair of the face, portions of the source 3D mesh where an angle of a normal at the portions meets a threshold angle, portions of the source 3D mesh that lie at least a threshold distance from the one or more landmarks identified in the source 3D mesh, and combinations thereof.
Pang teaches wherein the particular portions of the source 3D mesh are one or more of: portions of the source 3D mesh that correspond to hair of the face, portions of the source 3D mesh where an angle of a normal at the portions meets a threshold angle, portions of the source 3D mesh that lie at least a threshold distance from the one or more landmarks identified in the source 3D mesh, and combinations thereof. (Pang, Pg. 167213, “Figure2 shows the conformal mapping from a 3D surface to a planar area. TheheadofKingDavidinFig.2aisa3Dmodel obtained with a 3D scanner. It is a surface with complex geometric properties. On Fig. 2b, the 3D model is mapped to the 2D plane through conformal mapping. Figure 2b shows that although the curvature becomes zero, the details of the human face, including the shape of the eyebrows, nose, lips, and hair curls, are preserved.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including wherein the particular portions of the source 3D mesh are one or more of: portions of the source 3D mesh that correspond to hair of the face, portions of the source 3D mesh where an angle of a normal at the portions meets a threshold angle, portions of the source 3D mesh that lie at least a threshold distance from the one or more landmarks identified in the source 3D mesh, and combinations thereof as taught by Pang and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve portioned model transformation.
Regarding claim 4 and 14 Liu is silent about prior to determining the target 2D parameterization based on the template 3D mesh, obtaining a trimmed template 3D mesh by excluding portions of the template 3D mesh that meet specified criteria, and wherein determining the target 2D parameterization is based on the trimmed template 3D mesh.
Pang teaches prior to determining the target 2D parameterization based on the template 3D mesh (Pang, Pg. 167211, “The proposed model editing algorithm begins with selecting from a 3D model database a number of face models wearing different expressions, one of them being defined as the source model, from which a set of characteristic points are extracted. The rest of the selected face models are used, one by one, as the target models”), obtaining a trimmed template 3D mesh by excluding portions of the template 3D mesh that meet specified criteria (Pang, Pg. 167210, “Patel et al. [16] propose to use the features extracted from a given frontal facial image and transform an existing face model through geometric transformation.”), and wherein determining the target 2D parameterization is based on the trimmed template 3D mesh. (Pang, Pg. 167210, “First, multiple 3D face models with different expressions are selected. One is defined as the source model and the others as target models. Second, the source model and all target models are sequentially registered by the ICP algorithm, and the vertex correspondence is established. The registered models are parameterized to a 2D plane through quasi-conformal mapping.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including prior to determining the target 2D parameterization based on the template 3D mesh, obtaining a trimmed template 3D mesh by excluding portions of the template 3D mesh that meet specified criteria, and wherein determining the target 2D parameterization is based on the trimmed template 3D mesh as taught by Pang and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve portioned model transformation.
Regarding claim 8 and 18 Liu is silent about wherein the one or more landmarks identified in the source 3D mesh correspond to one or more of eyes, nose, and mouth.
Pang teaches wherein the one or more landmarks identified in the source 3D mesh correspond to one or more of eyes, nose, and mouth. (Pang, Pg. 167217, “The face models of a same person but with different facial expressions were tested in experiment. Figure 7a shows the source models, and Figure 7b and Figure 7c show the target models corresponding to different expressions. The characteristic points were mostly taken from the eyes and mouths of the models. From these points, constraints were developed for the editing of the source models.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including wherein the one or more landmarks identified in the source 3D mesh correspond to one or more of eyes, nose, and mouth as taught by Pang and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve alignments with landmarks.
Regarding claim 9 and 19 Liu is silent about further comprising simulating motion of parts of the face by simulating motion of points in the target 3D mesh that correspond to the parts of the face.
Pang teaches further comprising simulating motion of parts of the face by simulating motion of points in the target 3D mesh that correspond to the parts of the face. (Pang, Pg. 167217, “The face models of a same person but with different facial expressions were tested in experiment. Figure 7a shows the source models, and Figure 7b and Figure 7c show the target models corresponding to different expressions. The characteristic points were mostly taken from the eyes and mouths of the models. From these points, constraints were developed for the editing of the source models. The chosen characteristic points are given inFig.8a,Fig. 8bandFig.8c.Figure8d is the rendering of the parametric 2D plane of the source models. Figure 8e shows the starting position and target position maps of the characteristic points when deformation is completed on the 2D plane.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including further comprising simulating motion of parts of the face by simulating motion of points in the target 3D mesh that correspond to the parts of the face as taught by Pang and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve alignments with landmarks.
Regarding claim 10 and 20 Liu is silent about further comprising generating an image of the face based on the target 3D mesh by transferring one or more of a UV texture map, skinning, and animation routine from the template 3D mesh to the target 3D mesh.
Pang teaches further comprising generating an image of the face based on the target 3D mesh by transferring one or more of a UV texture map, skinning, and animation routine from the template 3D mesh to the target 3D mesh. (Pang, Pg. 167217, “FIGURE 8. Preprocessing of face models (a)Mesh model of source model; (b) Mesh mode of target model l; (c) Mesh model of target model 2 l; (d) The source model parameterized to a 2D plane l; (e) Red dots indicate starting positions, and blue ones ending positions. / FIGURE 10. Face model after editing (a) Intermediate model 1 after interpolation; (b) Target model 1; (c) Target model 2.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including further comprising generating an image of the face based on the target 3D mesh by transferring one or more of a UV texture map, skinning, and animation routine from the template 3D mesh to the target 3D mesh as taught by Pang and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve reconstruction of model from 2d to 3d.
Claim(s) 5 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu (Patent No. US 20180330480 A1) in view of Pang (NPL: Developing a Parametric 3D Face Model Editing Algorithm, 09/09/2020), in further view of Kang (Patent No. US 20220157020 A1), in further view of Liao (Patent No. US 20230306673 A1).
Regarding claim 5 and 15 Liu is silent about filling in portions of the target 3D mesh that correspond to the particular portions of the source 3D mesh by performing a constrained fit such that every point included in the target 3D mesh is exactly constrained and points corresponding to the particular portions of the source 3D mesh are deformed from the template 3D mesh.
filling in portions of the target 3D mesh that correspond to the particular portions of the source 3D mesh by performing a constrained fit such that every point included in the target 3D mesh is exactly constrained and points corresponding to the particular portions of the source 3D mesh are deformed from the template 3D mesh. (Liao, “[0079] As can be seen from FIGS. 3A and 3B, the rendering process comprises rendering of at least a portion of the surface of the 3D humanoid 240 itself that is exposed (such as the head 242, neck 244, arms 246, and legs 248 in FIGS. 3A and 3B) and rendering of the surface of the clothing (also called clothes, outfit, dress, or garment) of the 3D humanoid 240 (such as the shirt 252 and the short 254 in FIGS. 3A and 3B). Herein, the term “rendering” refers to the process using one or more textures or colors to fill the 3D surface of a 3D model such as the 3D humanoid”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including filling in portions of the target 3D mesh that correspond to the particular portions of the source 3D mesh by performing a constrained fit such that every point included in the target 3D mesh is exactly constrained and points corresponding to the particular portions of the source 3D mesh are deformed from the template 3D mesh as taught by Liao and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve portioned model transformation.
Claim(s) 6, 7, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liu (Patent No. US 20180330480 A1) in view of Pang (NPL: Developing a Parametric 3D Face Model Editing Algorithm, 09/09/2020), in further view of Kang (Patent No. US 20220157020 A1), in further view of Levy (NPL: Least Squares Conformal Maps for Automatic Texture Atlas Generation, 08/02/2023)
Regarding claim 6 and 16 Liu is silent about determining the target 2D parameterization of the template 3D mesh comprises applying a least squares conformal map (LSCM) technique to points of the template 3D mesh that lie outside the particular portions of the source 3D mesh.
Levy teaches determining the target 2D parameterization of the template 3D mesh comprises applying a least squares conformal map (LSCM) technique to points of the template 3D mesh that lie outside the particular portions of the source 3D mesh. (Levy, Pg. 198, “As shown in Figure 5, our algorithm can detect cylindrical shapes, as the approach proposed in [15]. In our case, two con f igurations can be distinguished: • The cylinder corresponds to an extremity, such as the ‘fingers’ of the dinosaur’s wings (Figure 5-B). The corresponding charts have the shape of a sock. This configuration is detected by com puting the area/perimeter ratio. In this case, to facilitate the pa rameterization phase, a cut is added by starting from the seed and cutting the edges along the steepest-descent path.”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including determining the target 2D parameterization of the template 3D mesh comprises applying a least squares conformal map (LSCM) technique to points of the template 3D mesh that lie outside the particular portions of the source 3D mesh. as taught by Levy and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve mapping with least squares conformal map.
Regarding claim 7 Liu is silent about determining the 2D parameterization of the second 3D mesh comprises applying a least squares conformal map (LSCM) technique to the second 3D mesh.
Levy teaches determining the 2D parameterization of the second 3D mesh comprises applying a least squares conformal map (LSCM) technique to the second 3D mesh. (Levy, Pg. 199, “Figure 8: Data sets and associated texture space constructed by our method”)
Therefore it would have been obvious for an ordinary skilled person in the art before the effective filing date of claimed invention to have modified Liu art by including determining the 2D parameterization of the second 3D mesh comprises applying a least squares conformal map (LSCM) technique to the second 3D mesh as taught by Levy and use that with Liu’s system and methods for generating and optimized 3D model.
The motivation for the combination is to improve mapping with least squares conformal map (LSCM).
Response to Arguments
Applicant's arguments filed 08/12/2026 have been fully considered but they are not persuasive.
Applicant argues Claim 6, as emphasized, applies the LSCM technique to "points of the template 3D mesh that lie outside the particular portions of the source 3D mesh." The cited Levy passage does not describe using excluded portions of a source mesh to determine which template-mesh points are parameterized.
Examiner replies that page 197 of Levy expressly states: “The segmentation algorithm decomposes the model into a set of charts. The design of the algorithm aims at meeting the following two requirements: 1. charts boundaries should be positioned in such a way that most of the discontinuities between the charts will be located in zones where they will not cause texture artifacts, 2. charts must be homeomorphic to discs, and it must be possible to parameterize them without introducing too much deformation.”. Thus, Levy teaches segmentation that separate source 3D mesh into portions, where excluded portions would be a user decision.
Regarding the remaining arguments: Applicant argues with respect to the amended claim language, which is fully addressed in the prior art rejections set forth below.
Conclusion: The rejections set forth in the previous Office Action are shown to have been proper, and the claims are rejected below. Inasmuch as new citations and parenthetical remarks can be considered new grounds of rejection, such new grounds of rejection are necessitated by Applicant’s amendments to the claims. Therefore, the present Office Action is made final.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAK FUNG A LAM whose telephone number is (571)272-9823. The examiner can normally be reached Monday-Friday 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Said Broome can be reached at 5712722931. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/C.A.L./Examiner, Art Unit 2612
/Said Broome/Supervisory Patent Examiner, Art Unit 2612
