DETAILED ACTION
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 .
Response to Arguments
Applicant’s arguments with respect amended claims 1, 2, 3, 5, 6, 7, 9 and 16 filed on 05/11/2026 have been considered but they are moot in view of the new ground(s) of rejection.
However, the examiner found some amended limitations are taught by references previous introduced.
In Remark page 12, second paragraph, applicant argued that In the claim 1, cited reference does not disclose or teach that the source image depicts an entity and the modification input indicates a target part and a target pose for the entity" and "wherein the output image depicts the entity with the target part and the target pose.
The examiner respectfully disagrees with Applicant’s argument. In fact, in Fig. 5, paragraph [0115], Petrangeli discloses “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504)” Petrangeli teaches the source image 501 (Fig. 5) depicts an entity (person is wearing a sleeveless shirt) indicates a target part (a sleeveless shirt) and a target pose (the arm of the person) and in the output image (image 502, 504) depicts an entity (person is wearing a sleeveless shirt) indicates a target part (a long sleeves shirt) and a target pose (the arm of the person).
Independent claims 1and 9 are rejected in view of the new ground(s) of rejection presented below with additional reference of Wang et al. (U.S. 2025/0378619 A1).
Dependent claims 2-8, 10-20, depend from independent claims 1, 9 and the rejections to the claims are maintained.
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 of this title, 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.
Claims 1-3, 5, 6, 8 and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable by Petrangeli et al. (U.S. 2023/0162330 A1) in view of Wang et al. (U.S. 2025/0378619 A1).
Regarding Claim 1 (Currently amended), Petrangeli discloses a method (Petrangeli, [0006] “a computer-implemented method for image”) comprising:
obtaining a source image (Petrangeli, [0029] “retaining the source image” and a modification input [0114] FIG. 5 shows a series of images 500 illustrating edited images generated using the techniques of FIG. 2” Petrangeli teaches obtain a source image (source images 501,511) as a modification input wherein the source image depicts an entity and the modification input indicates a target part and a target pose for the entity (Petrangeli, Fig. 5, [0115] “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504)” Petrangeli teaches the source image 501 (Fig. 5) depicts an entity (person is wearing a sleeveless shirt) indicates a target part (a sleeveless shirt) and a target pose (the arm of the person).
generating a part encoding based on the modification input, wherein the part encoding represents the target part (Petrangeli, [0033] “The shape editing subsystem generates a parsing map of the input image. The parsing map identifies regions of the input image such as the dress, arms, and legs of the person depicted in the image” and [0046] “The shape editing subsystem 110 includes an encoder that takes as input the source parsing map and generates a latent representation of the source parsing map” and Fig. 5, [0034] “The generated modified parsing map includes the target region of the dress with the specified shape change of long sleeves” Petrangeli teaches generating a part encoding based on modification encoding e.g., an encoder that takes as input the source parsing map, image 501, Fig. 5, which includes a target part, a sleeveless shirt, by a shape editing subsystem;
generating a pose-warped texture based on the modification input, wherein the pose-warped texture represents the target pose (Petrangeli, [0033] The parsing map identifies regions of the input image such as the dress, arms, and legs of the person depicted in the image” and Fig. 5, [0115] “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504)” Petrangeli teaches generating a pose-warped texture e.g., a person is wearing a sleeveless shirt on her arm (the target pose) Fig. 5, 501, as the modification input, is edited to have a long sleeves (502) (a pose-warped texture).
generating, using an image generation model, an output image (Petrangeli, [0045] “the image editing system 102 include trained machine learning models” and Fig. 1, [0046] “The shape editing subsystem 110 includes an encoder that takes as input the source parsing map and generates a latent representation of the source parsing map” and Fig. 1, [0053] “The appearance completion subsystem 130 takes as input the modified parsing map produced by the shape editing subsystem 110 and generates an output image 150” and Fig. 5, [0115] “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504)” Petrangeli teaches generating, using a trained machine learning model includes a shape editing subsystem, based on the part encoding input (by an encoder) (source image 501, Fig. 5) to output image (image 502, 504) depicts the entity (a person wearing a shirt) with the target part (a sleeveless shirt) and the target pose (arm of the person)
However, Petrangeli does not explicitly teach generating, using an image generation model, an output image by performing a denoising operation based on the part encoding and the pose-warped texture;
Wang teaches generating, using an image generation model, an output image by performing a denoising operation based on the part encoding and the pose-warped texture (Wang, [0069] “extract latent features by using a neural network (e.g., a variational autoencoder) to encode the lighting information into latent variables such as via: z=fencoder(I), where z is the latent vector, fencoder is the encoding function of the neural network, and I is the input image” and [0075] FIG. 2, a workflow for neural rendering. The DM 208 uses the provided information/inputs (i.e., 202, 204, 206, 212 and 214) to condition the denoising process, progressively refining the noisy input into a high-quality rendered image 210” Wang teaches generating, using an image generation model (the diffusion model, DM 208, Fig. 2), provide encoding input image of a neural network (i.e., 202, 204, 206, 212 and 214) to perform the denoising process for outputting a high-quality image 210.
Petrangeli and Wang are combinable because they are from the same field of endeavor, system and method for image processing and try to solve similar problems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made for modifying the method of Petrangeli to combine with performing a denoising operation (as taught by Wang) in order to generate an output image by performing a denoising operation based on the part encoding and the pose-warped texture because Wang can provide generating, using an image generation model (the diffusion model, DM 208, Fig. 2), provide encoding input image of a neural network (i.e., 202, 204, 206, 212 and 214) to perform the denoising process for outputting a high-quality image 210 (Wang, [0018] [0032] [0082]). Doing so, it may provide the iterative process (the denoising process) of a diffusion model allows users to see progressive improvements and changes in real-time or near real-time. This feedback loop is helpful for making fine adjustments and achieving the desired visual outcome efficiently (Wang [0040]).
Regarding Claim 2 (Currently amended), a combination of Petrangeli and Wang discloses the method of claim 1, wherein generating the part encoding comprises: encoding an image depicting a target replacement element for an element of the source image (Petrangeli, [0046] “The shape editing
subsystem 110 includes an encoder that takes as input the source parsing map and generates a latent representation of the source parsing map” and [0118] “results in the shape attribute editing task, even for asymmetric poses and challenging tasks that involve multiple regions to be edited, as in the cloth length manipulation” and [0119] FIG. 6, a single source image 602 presenting a challenging asymmetric pose” and [0120] In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited” Petrangeli teaches encoding an image (by an encoder) shows a target replacement element for an element of the source image (In columns 604, the target sleeve length is edited, and in columns 606, the target shirt length is edited, Fig. 6).
Regarding Claim 3 (Currently amended), a combination of Petrangeli and Wang discloses the method of claim 1, the pose-warped texture is generated based on the source image (Petrangeli, [0079] “the target region is a shirt, and the shirt is to be lengthened. The color, texture, and other properties of the shirt are extended into the masked region to lengthen the shirt and [0119] FIG. 6, a single source image 602 presenting a challenging asymmetric pose” and [0120] In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited” Petrangeli teaches generating a pose-warped texture based on the source image and the modification input based on the pose-warped texture e.g., a pose-warped texture of the arm of person (target pose) wearing a short-sleeved shirt (a pose-warped texture) in the source image 602 is modified with the sleeve length (604), or the shirt length (606), Fig. 6.
Regarding Claim 5 (Currently amended), a combination of Petrangeli and Wang discloses the method of claim 1, further comprising: identifying a background portion of the source image, wherein the output image is generated based on the background portion (Petrangeli, [0046] “The shape editing subsystem 110 includes an encoder that takes as input the source parsing map” and [0069] “the mapper 112 can be a neural network trained to generate a parsing map of an input image, where the parsing map identifies different regions of the image. For example, the parsing map separates the image into different regions such as a shirt, a face, an arm, a skirt, and a background” and Fig. 5, [0115] “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504)” Petrangeli teaches output image (image 502, Fig. 5) is generated based on the background region (a shirt of source image 501).
Regarding Claim 6 (Currently amended), a combination of Petrangeli and Wang discloses the method of claim 1, further comprising: obtaining a text prompt describing [[the]] a target edit (Petrangeli, Fig. 1, [0040] “the editor interface 104
responds to user selection of an upload element by transitioning to a view showing available files to upload, prompt a user to take a photo” and [0048] “An editor 115 manipulates the latent representation of the source parsing map to modify a shape of a target region” Petrangeli teaches obtaining a text prompt (from the editor interface) describing the target edit (modify a shape of a target region); and encoding the text prompt to obtain a text encoding, wherein the output image is generated based on the text encoding (Petrangeli, [0046] “The shape editing subsystem 110 includes an encoder that takes as input the source parsing map” and [0050] “The encoder 114 is a machine learning model trained to generate such a latent representation” Petrangeli teaches the editor interface includes a text prompt for user selection on input source image and encoder takes as input source to generate a text encoding (e.g., a latent representation).
Regarding Claim 8, a combination of Petrangeli and Wang discloses the method of claim 1, wherein: the modification input comprises at least one of a part replacement input or a pose modification (Petrangeli, [0049] “The encoder 14 includes one or more machine learning models trained to generate a latent representation of an input image” and [0118] “results in the shape attribute editing task, even for asymmetric poses and challenging tasks that involve multiple regions to be edited, as in the cloth length manipulation” and [0119] FIG. 6, a single source image 602 presenting a challenging asymmetric pose” and [0120] In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited” Petrangeli teaches the modification input (modify the appearance and the pose of a person wearing a shirt in source image 602, Fig. 6) includes a part replacement input (In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited, Fig. 6).
Regarding Claim 16 (Currently amended), a combination of Petrangeli and Wang discloses an apparatus (Petrangeli, [0139] “a general purpose computing apparatus”) comprising:
at least one processor (Petrangeli, [0125] “a processor 802”) ;
at least one memory storing instruction executable by the at least one processor (Petrangeli, [0125] “The processor 802 executes computer-executable program code stored in a memory device 804”;
a part encoder comprising parameters stored in the at least one memory and trained to generate a part encoding based on a source image and a part image indicating a target part, wherein the source image depicts an entity (Petrangeli, Fig. 1, [0056] “The generator 136 may be trained to produce an image by inpainting a specific region identified by the shape editing subsystem 110. In other words, the generator 136 generates a targeted region of the image (e.g., sleeves if sleeves are added, arms if sleeves are removed, and so forth) and Fig. 5, [0115] “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504). Source image 511, including a long-sleeved shirt, is edited so that the shirt depicted has short sleeves, with results shown for VPTNET (image 512), AMGAN (image 514)” Petrangeli teaches a part encoder (referred to as a generator 136) includes parameters e.g., sleeves and trained to generate a part based on a source image (source images 501, 511, Fig. 5) depicts an entity (a person wearing a shirt) and a part image indicating a target part e.g., sleeves if sleeves are added, arms if sleeves are removed, (image 502, image 512, Fig.5) ;
a condition encoder comprising parameters stored in the at least one memory and trained to generate a condition encoding based on the source image and pose information indicating a target pose (Petrangeli, Fig. 1, [0049] “The encoder 114 includes one or more machine learning models trained to generate a latent representation of an input image” and Fig. 5, [0115] “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504)” and [0118] “results in the shape attribute editing task, even for asymmetric poses and challenging tasks that involve multiple regions to be edited, as in the cloth length manipulation” Petrangeli teaches a condition encoder (encoder 114) includes parameters (e.g., sleeveless shirt, long sleeves) stored in memory and trained to generate a condition editing shape attribute (cloth length manipulation) base on source image (501, Fig. 5) a pose information indicating a target pose (arm of a person wearing a shirt, Fig. 5) ; and
an image generation model comprising parameters stored in the at least one memory and trained to generate an output image (Petrangeli, [0045] “the image editing system 102 include trained machine learning models” and Fig. 1, [0046] “The shape editing subsystem 110 generates a parsing map of an input image using a mapper 112. The parsing map is manipulated based on a target attribute specified by an edit parameter 108 to manipulate (e.g., sleeve or cloth length in an image including a clothing item). The shape editing subsystem 110 includes an encoder that takes as input the source parsing map and generates a latent representation of the source parsing map” and Fig. 5, [0115] “Source image 501, including a sleeveless shirt, is edited to have long sleeves, with results shown for VPTNET (image 502), AMGAN (image 504)” Petrangeli teaches an image generation model, a trained machine learning model (including a shape editing subsystem), includes parameters (sleeve, cloth length) stored in memory, to generate an output image (image 502, 504, Fig. 5) based on the includes a shape editing subsystem, based on the part encoding input (by an encoder) (source image 501, Fig. 5) to output image (image 502, 504) depicts the entity (a person wearing a shirt) with the target part (a sleeveless shirt) and the target pose (arm of the person;
However, Petrangeli does not explicitly teach an image generation model comprising parameters stored in the at least one memory and trained to generate an output image by performing a denoising operation based on the part encoding and the condition encoding;
Wang teaches an image generation model comprising parameters stored in the at least one memory and trained to generate an output image by performing a denoising operation based on the part encoding and the condition encoding (Wang, [0048] “some embodiments condition (e.g., via cross attention) the models on specific parameters (e.g., material maps, lighting, user input) and [0069] “extract latent features by using a neural network (e.g., a variational autoencoder) to encode the lighting information into latent variables such as via: z=fencoder(I), where z is the latent vector, fencoder is the encoding function of the neural network, and I is the input image” and [0075] FIG. 2, a workflow for neural rendering. The DM 208 uses the provided information/inputs (i.e., 202, 204, 206, 212 and 214) to condition the denoising process, progressively refining the noisy input into a high-quality rendered image 210” Wang teaches an image generation model (the diffusion model, DM 208, Fig. 2) include parameters (e.g., material maps, lighting, user input), provide encoding input image of a neural network (i.e., 202, 204, 206, 212 and 214) to perform the denoising process for outputting a high-quality image 210 based on the part encoding and the condition enconding.
Patrangeli and Wang are combinable see rationale in claim 1.
Regarding Claim 17, a combination of Petrangeli and Wang discloses the apparatus of claim 16, further comprising: a pose-warping mode configured to generate a pose-warped texture based on the source image and the pose information (Petrangeli, Fig. 2, [0066] “at 202, the image editing system (e.g., the shape editing subsystem) obtains an input image and an edit parameter, the input image depicts a person wearing a short-sleeved shirt, and the edit parameter specifies that the sleeves should be made longer” and [0079] “the target region is a shirt, and the shirt is to be lengthened. The color, texture, and other properties of the shirt are extended into the masked region to lengthen the shirt and [0119] FIG. 6, a single source image 602 presenting a challenging asymmetric pose” and [0120] In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited” Petrangeli teaches a pose-warping mode to generate a pose-warped texture based on the source image and the pose information e.g., a pose-warped texture of the person wearing a short-sleeved shirt (pose information) in the source image 602 is modified with the sleeve length (604), or the shirt length (606).
Regarding Claim 18, a combination of Petrangeli and Wang discloses the apparatus of claim 16, further comprising: a text encoder configured to generate a text encoding based on a text prompt (Petrangeli, Fig. 1, [0040] “the editor interface 104 responds to user selection of an upload element by transitioning to a view showing available files to upload, prompt a user to take a photo” and [0049] “The encoder takes as input the source parsing map and transforms it into a latent representation of the parsing map” and [0050] “The encoder 114 is a machine learning model trained to generate such a latent representation” and [0052] “The editor 115 applies changes to the latent representation based upon edit parameters 108” Petrangeli teaches the editor interface includes a text prompt for user selection on input source image and encoder takes as input source to generate a text encoding (e.g., a latent representation).
Regarding Claim 19, a combination of Petrangeli and Wang discloses the apparatus of claim 16, further comprising: a pose detector configured to generate the pose information based on the source image (Petrangeli, [0069] “The parsing map identifies regions in the input image including the target region, FIG. 1, the mapper 112 can be a neural network trained to generate a parsing map of an input image, where the parsing map identifies different regions of the image, the parsing map separates the image into different regions such as a shirt, a face, an arm, a skirt, and a background” Petrangeli teaches a pose detector (referred to as the mapper 112) to generate (identify) the pose information (different regions such as a shirt, a face, an arm, a skirt and a background) based on source image.
Regarding Claim 20, a combination of Petrangeli and Wang discloses the apparatus of claim 16, further comprising: a segmentation model configured to generate the part image based on the source image (Petrangeli, [0069] “The parsing map identifies regions in the input image including the target region, FIG. 1, the mapper 112 can be a neural network trained to generate a parsing map of an input image, where the parsing map identifies different regions of the image, the parsing map separates the image into different regions such as a shirt, a face, an arm, a skirt, and a background” Petrangeli teaches a segmentation model (referred to as a parsing map) to generate (separate) the image into different parts (regions) such as a shirt, a face, an arm, a skirt and a background, based on source image.
Claims 4, 7, and 9-15 are rejected under 35 U.S.C. 103 as being unpatentable by Petrangeli et al. (U.S. 2023/0162330 A1) in view of Wang et al. (U.S. 2025/0378619 A1) and further in view of Kheradmand et al. (U.S. 12,354,337 B1).
Regarding Claim 4, the method of claim 3, a combination of Petrangeli and Wang does not explicitly teach further comprising: selecting a mode from a set of pose-warping modes including a dense warping mode and a sparse warping mode, wherein the pose-warped texture is generated based on the selected mode.
However, Kheradmand teaches selecting a mode from a set of pose-warping modes including a dense warping mode (Kheradmand Col. 9 lines 5-10 “Garments are warped from the ith source pose PSi to the target pose PT, to synthesize the target garments. A DensePose-based garment deformation method can perform well with drastic view changes for the input images” Kheradmand teaches selecting a mode from a denspose wraping mode of a garment and a sparse warping mode (Kheradmand, Col. 3, lines 4-10 “Conventional techniques often take a single-view reference image as input. Even when garment warping is used, the quality suffers with drastic view changes due to occlusions and limited visible regions from a single view” Kheradmand teaches a sparse warping mode (a limited warping mode) of garment, wherein the pose-warped texture is generated based on the selected mode (Kheradmand, Col. 3, lines 1-3 “In addition, realistic garments are hard to synthesize. As non-rigid objects, the garments may fold and their texture may alter differently on different part of the human body” Kheradmand teaches the pose warped texture is generated based on the selected mode (the garments may fold and their texture may alter differently on different part of the human body).
Petrangeli, Wang and Kheradmand are combinable because they are from the same field of endeavor, system and method for image processing and try to solve similar problems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made for modifying the method of Petrangeli to combine with a dense warping mode and sparse warping mode (as taught by Kheradmand) in order to include a dense warping mode and a sparse warping mode because Kheradmand can provide selecting a mode from a denspose wraping mode of a garment and a sparse warping mode (a limited warping mode) of garment (Kheradmand, Col. 9 lines 5-10, Col. 3, lines 4-10). Doing so, it may provide directly synthesize human images to enhance textural quality and photorealism (Kheradmand, Col. 3, lines 17-18).
Regarding Claim 7(Currently amended), the method of claim [[1]] 6, a combination of Petrangeli and Wang does not explicitly teach wherein: the target edit comprises a replacement of at least one of an article of clothing, a hair style, a makeup style, or a body art style, and wherein the output image comprises a virtual try-on based on the replacement.
However, Kheradmand teaches the target edit comprises a replacement of at least one of an article of clothing, a hair style, a makeup style, or a body art style, and wherein the output image comprises a virtual try-on based on the replacement (Kheradmand, Col. 4 lines 29-33 “the request 112 may be a try-on request for a garment (e.g., a shirt) worn by an element (e.g., a person). The request 112 may include data that indicates an image that shows a shirt of a person in a target pose along with a try-on request of the shirt” Kheradmand teaches the target edit includes a replacement is an article of clothing (a shirt) and output image include a virtual try-on based on the replacement (try-on request of the shirt).
Petrangeli, Wang and Kheradmand are combinable see rationale in claim 4.
Regarding Claim 9 (Currently amended), a combination of Petrangeli and Wang discloses a method for training a machine learning model Petrangeli, [0006] “a computer-implemented method for image” and [0045] “the image editing system 102 include trained machine learning models”), the method comprising:
obtaining a training set including a ground-truth image depicting an entity, pose information indicating a target pose of the entity (Petrangeli, [0044] “the shape editing subsystem 110 could be a separate entity from the appearance…the training subsystem 140, or the same entity” and [0069] “the parsing map separates the image into different regions such as a shirt, a face, an arm, a skirt, and a background. These regions may be defined using binary attributes corresponding to the semantic parsing of the elements of a target image” Petrangeli teaches , and a part image depicting a target part of the entity (Petrangeli, [0119] FIG. 6, a single source image 602 presenting a challenging asymmetric pose” and [0120] In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited” Petrangeli teaches a part image (Fig. 6) shows a target part of the entity (the sleeve, the shirt are edited, Fig. 6).
training, using the training set , an image generation model to generate an output image that depicts the entity with the target pose and the target part (Petrangeli, [0119] FIG. 6, a single source image 602 presenting a challenging asymmetric pose” and [0120] In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited” Petrangeli teaches training, using the training set (source image 602) to edit shape attribute (cloth length manipulation) base on source image to output image depicts the entity (sleeve, shirt) with the target pose (the pose of a person wearing a shirt in source image 602 presenting an asymmetric pose, Fig. 6) and target part (In columns 604, the sleeve length is edited, and in columns 606, the shirt length is edited).
However, Petrangeli does not explicitly teach
generating a noise prediction based on the pose information and the part image;
training, using the training set and the noise prediction,
a ground-truth image depicting an entity, pose information.
Wang teaches generating a noise prediction based on the pose information and the part image; training, using the training set and the noise prediction (Wang, [0039] “During training, the model learns to predict the final rendered frame by progressively refining noisy inputs using the scene properties. During actual usage (inference), the model receives a noise vector and the representations of material and lighting maps, processes them through iterative denoising steps, and outputs the final rendered frame” Wang teaches during the training, generating a noise prediction to refining noisy inputs using the scene properties such a noise vector (referred to as a pose information) and the part image (the representation of material).
Petrangeli and Wang are combinable see rationale in claim 1.
Kheradmand teaches a ground-truth image depicting an entity, pose information (Kheradmand, Col. 8 lines 33-36 “The output ML model 562 may further be trained based on a distance minimization between a generated image and a ground truth image in a feature space” and Col. lines “The first image may be input to an ML model, which can output pose data of the first pose…poses include front upper body, front full body, left side view, right side view, back upper body, back lower body, etc” Kheradmand teaches a ground truth image depicting an entity (body), pose information (upper body, lower body etc.)
Petrangeli, Wang and Kheradmand are combinable see rationale in claim 4.
Regarding Claim 10, the method of claim 9, a combination of Petrangeli and Wang does not explicitly teach wherein training the image generation model comprises: computing a multi-task loss function including an entity-part loss term and a pose-warp loss term; and updating parameters of the image generation model based on the multi-task loss function.
However, Kheradmand teaches computing a multi-task loss function including an entity-part loss term and a pose-warp loss term (Kheradmand, Col. 3 lines 36-37 “A conditional patch loss is also introduced to improve the fidelity and details of the generated images” and Col. 10 lines 56-60 “Another training loss is a combination of the above-mentioned loss functions: L=LGAN+λ1Lrec+λ2Lface+λ3Lpatch, and Col. 10 lines 41-43 “In addition to the patch loss Lpatch, the full image adversarial LGAN used in StyleGAN2, and the face identify loss Lface used in PWS” Kheradmand teaches a multi-task loss function (L) includes an entity-part loss term (LGAN used in part of StyleGAN2) and a pose-warp loss term (the pose of face identify loss Lface used in PWS); and updating parameters of the image generation model based on the multi-task loss function (Kheradmand, Col. lines “The output ML model 562 may be a conditional patch discriminator Dpatch that enforces the realism of patches… The corresponding patch loss for the discriminator is calculated as: Lpatch= E[log(Dpatch(patch(LT),patch(IT)|patch(IS)))] (2)” Kheradmand teaches updating (caculating) parameters (patchs) of the image generation model (ML model 562) based the multi-task loss function (Lpatch).
Petrangeli, Wang and Kheradmand are combinable see rationale in claim 4.
Regarding Claim 11, the method of claim 10, a combination of Petrangeli and Wang does not explicitly teach wherein: the entity-part loss term is based on a segmentation map for the target part of the entity.
However, Kheradmand teaches the entity-part loss term is based on a segmentation map for the target part of the entity (Kheradmand, Col. 3 lines 36-37 “A conditional patch loss is also introduced to improve the fidelity and details of the generated images” and Col. 9 lines 13-17 “For a source appearance image ISi of the ith view, an upper body garment and a lower body garment are segmented with an off-the-shelf clothed human image segmentation algorithm. The upper and lower body garments go through the same procedure for deforming to the target pose” Kheradmand teaches the entity-part loss term based on a segmentation map for the target part of the entity (an upper body garment and a lower body garment are segmented with an off-the-shelf clothed human).
Petrangeli, Wang and Kheradmand are combinable see rationale in claim 4.
Regarding Claim 12, the method of claim 10, a combination of Petrangeli and Wang does not explicitly teach wherein: the pose-warp loss term is based on a visibility map corresponding to the target pose of the entity.
However, Kheradmand teaches the pose-warp loss term is based on a visibility map corresponding to the target pose of the entity (Kheradmand, Col. 3, lines 36-37 “A conditional patch loss is also introduced to improve the fidelity and details of the generated images” and Fig. 6, Col. 8, lines 3-10 “A visibility map may additionally be used to generate the appearance feature for each of the input images 540A-C… The visibility map is determined based on the pose and the target pose, where the visibility map indicates a region in the target image that is also available in the input image” and Col. 12, lines 22-24 “The warping may involve a TPS transformation that transforms the garment to the target pose using the visibility map” Kheradmand teaches the pose-warp loss term (patch loss is used on details of the generated image, warped images) is based on a visibility map corresponding to the target pose of the entity (the garment), Fig. 6.
Petrangeli, Wang and Kheradmand are combinable see rationale in claim 4.
Regarding Claim 13, a combination of Petrangeli, Wang and Kheradmand discloses the method of claim 10, wherein: the multi-task loss function includes a diffusion loss term (Petrangeli, [0008] “a loss function comprising the reconstruction loss, the adversarial loss, and the attribute manipulation loss” and [0094] “while the reconstruction loss and adversarial loss teach the second neural network to accurately reproduce the input parsing map” Petrangeli teaches the loss function includes a diffusion loss term (referred to as the reconstruction loss to accurately reproduce the input parsing map).
Regarding Claim 14, a combination of Petrangeli, Wang and Kheradmand discloses the method of claim 9, wherein obtaining the training set comprises: applying a pose detection model to the ground-truth image to the pose information (Petrangeli, [0069] “The parsing map identifies regions in the input image including the target region, FIG. 1, the mapper 112 can be a neural network trained to generate a parsing map of an input image, where the parsing map identifies different regions of the image, the parsing map separates the image into different regions such as a shirt, a face, an arm, a skirt, and a background” Petrangeli teaches applying a pose detector (referred to as the mapper 112) to the ground-truth image (referred to as the input image including the target region) to the pose information (different regions such as a shirt, a face, an arm, a skirt and a background) based on source input image.
Regarding Claim 15, a combination of Petrangeli, Wang and Kheradmand discloses the method of claim 9, wherein obtaining the training set comprises: applying a segmentation model to the ground-truth image to obtain the part image (Petrangeli, [0069] “The parsing map identifies regions in the input image including the target region, FIG. 1, the mapper 112 can be a neural network trained to generate a parsing map of an input image, where the parsing map identifies different regions of the image, the parsing map separates the image into different regions such as a shirt, a face, an arm, a skirt, and a background” Petrangeli teaches applying a segmentation model (referred to as a parsing map) to the ground-truth image (referred to as the input image including the target region) to obtain the part image e.g., different parts (regions) of image such as a shirt, a face, an arm, a skirt and a background, based on source input image.
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 KHOA VU whose telephone number is (571)272-5994. The examiner can normally be reached 8:00- 4:00.
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, Kee Tung can be reached at 571-272-7794. 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.
/KHOA VU/Examiner, Art Unit 2611
/KEE M TUNG/Supervisory Patent Examiner, Art Unit 2611
Prosecution Insights