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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 09/09/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1, 6-8, 13, 16, and 20-22 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Aigerman (US 20230281925 A1).
Regarding claim 1, Aigerman teaches a method, comprising:
receiving, by a processing device, a subject image depicting a subject person (par. 0032: “Additionally, in some embodiments, the three-dimensional mesh system 110 receives data from the client device 106 in connection with editing three-dimensional meshes, including requests to access three-dimensional meshes or digital source images stored at the server device(s) 104 (or at another device such as a source repository) and/or requests to store three-dimensional meshes from the client device 106 at the server device(s) 104 (or at another device).”), a pose selection specifying a pose for the subject person (par. 0056: “To illustrate, the mesh mapping system 102 obtains the global code 304 from a previously generated database of encodings representing target shapes or poses for the three-dimensional mesh 300 or other three-dimensional meshes (e.g., based on skinned multi-person linear model pose parameters).”), and target pose data associated with the pose selection (par. 0022: “In additional embodiments, the mesh mapping system generates a modified three-dimensional mesh including vertices based on a mapping. To illustrate, the mesh mapping system utilizes the mapping to modify a shape of a three-dimensional mesh on which the mapping is based according to a target pose of the three-dimensional mesh.”), the target pose data describing one or more dimensions that specify positions and orientations of body parts of a reference human model in the pose of the pose selection (par. 0044: “As used herein, the term “mapping” refers to a plurality of values indicating translation/transformation of a plurality of vertices of a multi-dimensional mesh from a first position in a multi-dimensional space to a second position in a multi-dimensional space. For example, a mapping corresponds to movement of one or more portions of a three-dimensional mesh from one position to another position in the same three-dimensional space. To illustrate, a mapping includes a re-posing of a three-dimensional mesh from a first pose to a second pose, such as changing relative positions of limbs of a three-dimensional human model.”);
determining, using a first machine-learning model and the subject image, measurements of the subject person, the measurements relatable to the one or more dimensions described by the target pose data (par. 0022, as above);
generating, based on the measurements, a mesh representing the subject person (par. 0032: “In some embodiments, the three-dimensional mesh system 110 receives interaction data for viewing, generating, or editing a three-dimensional mesh from the client device 106, processes the interaction data (e.g., to view, generate, or edit a three-dimensional mesh), and provides the results of the interaction data to the client device 106 for display via the digital image application 114 or to a third-party system.”);
generating, using a second machine-learning model, mappings between the mesh and the target pose data, the mappings describing connections between portions of the mesh and the positions and orientations of the body parts of the reference human model (par. 0033: “In connection with providing tools for interacting with three-dimensional meshes, the three-dimensional mesh system 110 utilizes the mesh mapping system 102 to generate mappings for three-dimensional meshes and/or to generate modified three-dimensional meshes.”);
generating, using the second machine-learning model, a model of the subject person in the pose of the pose selection based on the measurements, the mesh, the mappings, and the target pose data (par. 0094: “FIG. 7 illustrates that the mesh mapping system 102 utilizes a mapping generation model (including a trained neural network) to generate mappings for a plurality of different poses. In particular, as mentioned, the mesh mapping system 102 provides a global code representing a target pose to the mapping generation model to create a mapping based on the target pose. “); and
displaying, by the processing device, a pose-transferred image depicting the subject person in the pose of the pose selection based on the model of the subject person (par. 0034: “In one or more embodiments, in response to utilizing the mesh mapping system 102 to generate a mapping and/or a modified three-dimensional mesh, the three-dimensional mesh system 110 provides the resulting mapping and/or modified three-dimensional mesh to the client device 106 for display.”).
Regarding claim 6, Aigerman teaches the method of claim 1, wherein the first machine-learning model is a parametric model that generates the mesh representing the subject person based on the measurements (par. 0057: “In some instances, the mesh mapping system 102 determines a set of parameters directly defining specific properties of a target pose or shape (e.g., a set of angles, rotation/translation values, or other parameters).”).
Regarding claim 7, Aigerman teaches the method of claim 6, wherein the target pose data includes a mesh of the reference human model in the pose of the pose selection, and the second machine-learning model transforms the mesh representing the subject person based on the mesh of the reference human model (par. 0056: “In additional embodiments, the mesh mapping system 102 determines a global code 304 corresponding to the three-dimensional mesh 300. Specifically, the mesh mapping system 102 determines the global code 304 including a vector that represents a target shape of the three-dimensional mesh 300 or a target pose associated with the three-dimensional mesh 300.”).
Regarding claim 8, Aigerman teaches the method of claim 7, wherein transforming the mesh representing the subject person based on the mesh of the reference human model includes maintaining a size and proportion of body parts represented by the mesh representing the subject person while adjusting a position or orientation of the body parts based on the mesh of the reference human model (par. 0026: “ In particular, the mesh mapping system generates detail-preserving mappings by restricting an extrinsic field of linear transformations in the ambient space to an intrinsic field of linear transformations in the tangent spaces of corresponding triangles/polygons of a three-dimensional mesh. The mesh mapping system further retains greater detail during mesh transformations via the use of a Poisson model that leverages a differential operator specific to the three-dimensional model. Thus, the mesh mapping system utilizes a neural network-based model to provide flexible and accurate mesh mappings that are agnostic to the specific triangulations of the three-dimensional meshes while also preserving greater detail in the three-dimensional meshes than conventional systems.”).
Claim 13 is substantially similar to claim 1, except that it teaches a computing device rather than a method. As such, it is rejected on a similar basis to claim 1.
Claim 16 is substantially similar to claim 6, except that it depends from claim 13 instead of claim 1. As such, it is rejected on a similar basis to claim 6.
Claim 20 is substantially similar to claim 1, except that it teaches computer-readable storage media rather than a method. As such, it is rejected on a similar basis to claim 1.
Regarding claim 21, Aigerman teaches the method of claim 1, wherein determining the measurements includes determining, based on measurements of portions of the subject person that are visible in the subject image, a measurement of a portion of the subject person that is not visible in the subject image (par. 0029: “As used herein, the term “neural network” refers to one or more computer algorithms that can be tuned (e.g., trained) based on inputs to approximate unknown functions. In particular, a neural network can include a machine-learning model that utilizes algorithms to learn from, and make determinations on, known data by analyzing the known data to learn to generate outputs that reflect patterns and attributes of the known data. For instance, a neural network can include, but is not limited to, a multilayer perceptron or a convolutional neural network. A neural network can learn high-level abstractions in data to generate data-driven determinations, predictions, or decisions from the known input data.”).
Regarding claim 22, Aigerman teaches the method of claim 1, wherein the second machine-learning model includes a parametric body model trained on mappings between mesh models and target pose data to generate pose-transferred mesh models (par. 0057: “In some instances, the mesh mapping system 102 determines a set of parameters directly defining specific properties of a target pose or shape (e.g., a set of angles, rotation/translation values, or other parameters).”).
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) 2-4, 9-12, 14, and 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Aigerman (US 20230281925 A1) as applied to claims 1, 13, and 20 above, and further in view of Koujan (US 20240127563 A1).
Regarding claim 2, Aigerman teaches the method of claim 1, but fails to teach:
receiving, by the processing device, a garment selection specifying a garment for the subject person;
determining, using a third machine-learning model, a fit of the garment on the subject person based on a garment image depicting the garment worn by another person and the measurements of the subject person; and
generating, by the processing device, the pose-transferred image, where the pose-transferred image portrays the subject person wearing the garment in the pose.
Koujan teaches receiving, by the processing device, a garment selection specifying a garment for the subject person (par. 0032: “The user can select a given one of the identifiers to launch the corresponding AR experience or perform a desired image modification (e.g., replacing a garment being worn by a user in a video or morphing, changing, blending or transforming a portion of a body of a person or user into an AR graphic, such as an AR werewolf or AR bat).”);
determining, using a third machine-learning model, a fit of the garment on the subject person based on a garment image depicting the garment worn by another person and the measurements of the subject person (par. 0058: “The messaging client 104 controls the type of user data that is shared with external resources based on the type of external resource being authorized. For example, external resources that include full-scale external applications (e.g., a third-party or external application 109) are provided with access to a first type of user data (e.g., only 2D avatars of users with or without different avatar characteristics). As another example, external resources that include small-scale versions of external applications (e.g., web-based versions of third-party applications) are provided with access to a second type of user data (e.g., payment information, 2D avatars of users, 3D avatars of users, and avatars with various avatar characteristics). Avatar characteristics include different ways to customize a look and feel of an avatar, such as different poses, facial features, clothing, and so forth.”); and
generating, by the processing device, the pose-transferred image, where the pose-transferred image portrays the subject person wearing the garment in the pose (par. 0082: “A transformation system can capture an image or video stream on a client device (e.g., the client device 102) and perform complex image manipulations locally on the client device 102 while maintaining a suitable user experience, computation time, and power consumption. The complex image manipulations may include size and shape changes, emotion transfers (e.g., changing a face from a frown to a smile), state transfers (e.g., aging a subject, reducing apparent age, changing gender), style transfers, graphical element application, 3D human pose estimation, 3D body mesh reconstruction, and any other suitable image or video manipulation implemented by a convolutional neural network that has been configured to execute efficiently on the client device 102.”).
It would have been obvious to one familiar in the art prior to the effective filing date of the claimed invention to include the garment-rendering method of Koujan into the three-dimensional mesh mapping of Aigerman, as all are in the same field of endeavor of three-dimensional mapping with neural networks. Doing so would allow the invention of Aigerman to render clothing on human models, which would be obviously beneficial to one wishing to generate models of human figures.
Regarding claim 3, Aigerman and Koujan teach the method of claim 2. Koujan further teaches selecting, using a convolutional neural network, the garment image from a plurality of candidate images depicting the garment worn in different poses based on similarity between a pose depicted by the garment image and the pose specified by the pose selection (par. 0080: “One shape is aligned to another with a similarity transform (allowing translation, scaling, and rotation) that minimizes the average Euclidean distance between shape points.”), the similarity determined by the convolutional neural network (par. 0117: “In some examples, the neural network may also be one of a number of different types of neural networks, including a single-layer feed-forward network, an Artificial Neural Network (ANN), GAN, a Recurrent Neural Network (RNN), a symmetrically connected neural network, and unsupervised pre-trained network, a Convolutional Neural Network (CNN), or a Recursive Neural Network (RNN), merely for example.”).
Regarding claim 4, Aigerman teaches the method of claim 1, but fails to teach wherein the pose selection is received via user input selecting the pose selection from a plurality of target poses, where each target pose of the plurality of target poses is associated with respective target pose data.
Koujan teaches pose selection received via user input selecting the pose selection from a plurality of target poses, where each target pose of the plurality of target poses is associated with respective target pose data (par. 0021: “As a result, a realistic display can be provided that shows the user or person being stylized according to a selected or given style while moving around a video in 3D, including changes to the body shape, body state, body style and visual attributes, body properties, position, and rotation, in a way that is intuitive for the user to interact with and select.”).
It would have been obvious to one familiar in the art prior to the effective filing date of the claimed invention to include the garment-rendering method of Koujan into the three-dimensional mesh mapping of Aigerman, as all are in the same field of endeavor of three-dimensional mapping with neural networks. Doing so would allow the invention of Aigerman to render clothing on human models, which would be obviously beneficial to one wishing to generate models of human figures.
Regarding claim 9, Aigerman teaches the method of claim 1, but fails to teach wherein the subject image of the subject person depicts the subject person wearing a garment, and the pose-transferred image depicts the subject person in the pose of the pose selection while wearing the garment.
Koujan teaches wherein the subject image of the subject person depicts the subject person wearing a garment, and the pose-transferred image depicts the subject person in the pose of the pose selection while wearing the garment (par. 0032: “The user can select a given one of the identifiers to launch the corresponding AR experience or perform a desired image modification (e.g., replacing a garment being worn by a user in a video or morphing, changing, blending or transforming a portion of a body of a person or user into an AR graphic, such as an AR werewolf or AR bat).”).
It would have been obvious to one familiar in the art prior to the effective filing date of the claimed invention to include the garment-rendering method of Koujan into the three-dimensional mesh mapping of Aigerman, as all are in the same field of endeavor of three-dimensional mapping with neural networks. Doing so would allow the invention of Aigerman to render clothing on human models, which would be obviously beneficial to one wishing to generate models of human figures.
It would have been obvious to one familiar in the art prior to the effective filing date of the claimed invention to include the garment-rendering method of Koujan into the three-dimensional mesh mapping of Aigerman, as all are in the same field of endeavor of three-dimensional mapping with neural networks. Doing so would allow the invention of Aigerman to render clothing on human models, which would be obviously beneficial to one wishing to generate models of human figures.
Regarding claim 10, Aigerman teaches the method of claim 1, but fails to teach determining, using a third machine-learning model, similarity between a pose of the subject person in the subject image and poses of a pose set, and outputting a recommendation for the pose selection based on the similarity.
Koujan teaches determining, using a third machine-learning model, similarity between a pose of the subject person in the subject image and poses of a pose set, and outputting a recommendation for the pose selection based on the similarity (par. 0080: “One shape is aligned to another with a similarity transform (allowing translation, scaling, and rotation) that minimizes the average Euclidean distance between shape points.”).
It would have been obvious to one familiar in the art prior to the effective filing date of the claimed invention to include the garment-rendering method of Koujan into the three-dimensional mesh mapping of Aigerman, as all are in the same field of endeavor of three-dimensional mapping with neural networks. Doing so would allow the invention of Aigerman to render clothing on human models, which would be obviously beneficial to one wishing to generate models of human figures.
Regarding claim 11, Aigerman teaches the method of claim 1, but fails to teach wherein training data for the second machine-learning model includes pairs of images of persons in different poses to learn to transfer the poses between the persons.
Koujan teaches wherein training data for the second machine-learning model includes pairs of images of persons in different poses to learn to transfer the poses between the persons (par. 0125: “The body stylizing system 224 generates a pair of images of the training data by applying a new latent code to the first and second whole-body GANs to generate a first of the plurality of training images depicting synthetically rendered whole bodies of persons and a first of the ground-truth stylized versions of the whole bodies of the persons. In some examples, the body stylizing system 224 trains the machine learning model based on the paired images of the training data.”).
It would have been obvious to one familiar in the art prior to the effective filing date of the claimed invention to include the garment-rendering method of Koujan into the three-dimensional mesh mapping of Aigerman, as all are in the same field of endeavor of three-dimensional mapping with neural networks. Doing so would allow the invention of Aigerman to render clothing on human models, which would be obviously beneficial to one wishing to generate models of human figures.
Regarding claim 12, Aigerman teaches the method of claim 1, but fails to teach wherein the model of the subject person in the pose of the pose selection is a pose-transferred mesh, and the pose-transferred image is generated using a generative adversarial neural network that synthesizes a portrayal of the subject person on the pose-transferred mesh.
Koujan teaches wherein the model of the subject person in the pose of the pose selection is a pose-transferred mesh, and the pose-transferred image is generated using a generative adversarial neural network that synthesizes a portrayal of the subject person on the pose-transferred mesh (par. 0082: “A transformation system can capture an image or video stream on a client device (e.g., the client device 102) and perform complex image manipulations locally on the client device 102 while maintaining a suitable user experience, computation time, and power consumption. The complex image manipulations may include size and shape changes, emotion transfers (e.g., changing a face from a frown to a smile), state transfers (e.g., aging a subject, reducing apparent age, changing gender), style transfers, graphical element application, 3D human pose estimation, 3D body mesh reconstruction, and any other suitable image or video manipulation implemented by a convolutional neural network that has been configured to execute efficiently on the client device 102.”).
It would have been obvious to one familiar in the art prior to the effective filing date of the claimed invention to include the garment-rendering method of Koujan into the three-dimensional mesh mapping of Aigerman, as all are in the same field of endeavor of three-dimensional mapping with neural networks. Doing so would allow the invention of Aigerman to render clothing on human models, which would be obviously beneficial to one wishing to generate models of human figures.
Claim 14 is substantially similar to claim 2, except that it depends from claim 13 instead of claim 1. As such, it is rejected on a similar basis to claim 2.
Claim 17 is substantially similar to claim 10, except that it depends from claim 13 instead of claim 1. As such, it is rejected on a similar basis to claim 10.
Claim 18 is substantially similar to claim 11, except that it depends from claim 13 instead of claim 1. As such, it is rejected on a similar basis to claim 11.
Claim 19 is substantially similar to claim 12, except that it depends from claim 13 instead of claim 1. As such, it is rejected on a similar basis to claim 12.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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 RYAN A BARHAM whose telephone number is (571)272-4338. The examiner can normally be reached Mon-Fri, 8:30am-5pm EST.
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, Xiao Wu can be reached at (571) 272-7761. 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.
/RYAN ALLEN BARHAM/Examiner, Art Unit 2613
/XIAO M WU/Supervisory Patent Examiner, Art Unit 2613
Prosecution Insights