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 November 13, 2024; June 30, 2025; December 04, 2025 and February 20, 2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement has been considered by the examiner.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 1, 4, 6 – 13 and 16 – 20 are rejected under 35 U.S.C 103 as being unpatentable over Tensemeyer et al. US Patent Publication No. US-20220277431-A1 (hereinafter Tensemeyer) in view of Zhang US Patent Application Publication No. US-20210264235-A1 (hereinafter Zhang).
Regarding claim 1, Tensemeyer discloses computer-implemented method (Tensemeyer in [0116] discloses, “the components 902-908 can comprise one or more instructions stored on a computer-readable storage medium and executable by processor of one or more computing devices”), comprising: identifying, by one or more processors for each image of a set of images of a subject, a given code from among a set of codes in a vector space (Tensemeyer in [0097] discloses, “the image projection system 106 also utilizes the learned-initialization-latent vector Z.sub.INIT to generate learned-latent vectors that, when processed by an image-generating-neural network, convert into reconstructed versions of each of the remaining digital images from the digital image batch 502 (e.g., a learned-latent vector Z.sub.N for digital image N)” wherein “digital image batch 502” equates to set of image and ‘learned latent vector” implies to give code. Additionally, Tensemeyer in [0030] discloses about images of subject, “the term “digital image” (sometimes referred to as “image”) refers to a digital symbol, picture icon, and/or other visual illustration depicting one or more objects. For instance, an image includes a digital file having a visual illustration and/or depiction of a person or a face (e.g., a portrait image)”), generating, by the one or more processors using a generative model (Tensemeyer in [0034] discloses, “the image-generating-neural network includes a generative adversarial neural network (GAN) ... to generate facial images from latent vectors”), a personalized prior for the subject, the personalized prior corresponding to the given code for each image of the set of images (Tensemeyer in [0097] discloses “generates learned-latent vector Z.sub.2” (given code) through learned-latent vector Z.sub.N for digital images 2 to N from the digital image (set of image), “the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N”).
Tensemeyer doesn’t disclose about the following limitation as further recited in the claim.
Zhang discloses the given code having a lowest loss value, and each code of the set of codes corresponds to a respective one of the set of images of the subject (Zhang in [0058] discloses, “At each iteration, the projection module 206 generates N samples (multiple samples, such as N=10) of zi from the Gaussian. The projection module 206 determines the loss between the target image 116 and the image generated from each of the latent-class vector pairs (z, c)i and performs a Covariance Matrix Adaptation (CMA) update using the optimized z vector having the lowest loss (the lowest value of the loss function)”).
It would have been obvious to one of ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Zhang into the system of Tensemeyer because it would allow the system to reduce the likelihood of using a latent code that poorly represents that corresponding subject image.
Summary of Citations (Zhang)
Paragraph [0058]; “At each iteration, the projection module 206 generates N samples (multiple samples, such as N=10) of zi from the Gaussian. The projection module 206 determines the loss between the target image 116 and the image generated from each of the latent-class vector pairs (z, c)i and performs a Covariance Matrix Adaptation (CMA) update using the optimized z vector having the lowest loss (the lowest value of the loss function)”.
Summary of Citations (Tensemeyer)
Paragraph [0030]; “the term “digital image” (sometimes referred to as “image”) refers to a digital symbol, picture icon, and/or other visual illustration depicting one or more objects. For instance, an image includes a digital file having a visual illustration and/or depiction of a person or a face (e.g., a portrait image)”.
Paragraph [0034]; “the image-generating-neural network includes a generative adversarial neural network (GAN) ... to generate facial images from latent vectors”.
Paragraph [0097]; “the image projection system 106 also utilizes the learned-initialization-latent vector Z.sub.INIT to generate learned-latent vectors that, when processed by an image-generating-neural network, convert into reconstructed versions of each of the remaining digital images from the digital image batch 502 (e.g., a learned-latent vector Z.sub.N for digital image N). Indeed, in one or more embodiments, the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N)”.
Paragraph [0116]; “the components 902-908 can comprise one or more instructions stored on a computer-readable storage medium and executable by processor of one or more computing devices. When executed by the one or more processors, the computer-executable instructions of the image projection system 106”.
Regarding claim 4, Tensemeyer in the combination discloses the method of claim 1, further comprising generating, using the personalized prior, a set of candidate images for a given image enhancement task (Tensemeyer in [0097] discloses learned-latent vector Z.sub.N for digital images 2 to N from the digital image (set of image), “the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N” wherein learned prior equates to personalized prior. Additionally, Tensemeyer in [0091] discloses about modifying image attributes (image enhancement task), “the specific portion of the learned-latent vector, the image projection system 106 modifies the specific portion to modify the particular attribute (e.g., lighting, color, background details, foreground details, and/or textures) within a modified version of the target digital image”).
Summary of Citations (Tensemeyer)
Paragraph [0091]; “the specific portion of the learned-latent vector, the image projection system 106 modifies the specific portion to modify the particular attribute (e.g., lighting, color, background details, foreground details, and/or textures) within a modified version of the target digital image”.
Paragraph [0097]; “the image projection system 106 also utilizes the learned-initialization-latent vector Z.sub.INIT to generate learned-latent vectors that, when processed by an image-generating-neural network, convert into reconstructed versions of each of the remaining digital images from the digital image batch 502 (e.g., a learned-latent vector Z.sub.N for digital image N). Indeed, in one or more embodiments, the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N)”.
Regarding claim 6, Tensemeyer in the combination discloses the method of claim 1, wherein the vector space is at least a two-dimensional vector space (Tensemeyer in [0038] discloses about latent vector containing a set of feature values (at least two dimensional vector space), “the latent values of a latent-feature vector include latent or custom features that an image-generating-neural network is trained to identify features, such as, but not limited to, object height, width, shape, color, object features (e.g., eyes, nose, mouth, hair), or pixel intensities”).
Summary of Citations (Tensemeyer)
Paragraph [0038]; “the latent values of a latent-feature vector include latent or custom features that an image-generating-neural network is trained to identify features, such as, but not limited to, object height, width, shape, color, object features (e.g., eyes, nose, mouth, hair), or pixel intensities”.
Regarding claim 7, Tensemeyer in the combination discloses the method of claim 1, wherein the generative model comprises a generative adversarial network (Tensemeyer in [0034] discloses, “the image-generating-neural network includes a generative adversarial neural network (GAN) ... to generate facial images from latent vectors”).
Summary of Citations (Tensemeyer)
Paragraph [0034]; “the image-generating-neural network includes a generative adversarial neural network (GAN) ... to generate facial images from latent vectors”.
Regarding claim 8, Tensemeyer in the combination discloses the method of claim 1, further comprising tailoring the set of images to correspond to a particular phase of life associated with the subject (Tensemeyer in [0090] discloses, “the image projection system 106 modifies the learned-latent vector of the target digital image to modify (or transfer) the gender, age, and/or skin color of a person depicted within a modified version of the target digital image”).
Summary of Citations (Tensemeyer)
Paragraph [0090]; “the image projection system 106 modifies the learned-latent vector of the target digital image to modify (or transfer) the gender, age, and/or skin color of a person depicted within a modified version of the target digital image”.
Regarding claim 9, Tensemeyer in the combination discloses the method of claim 1, further comprising tailoring the set of images to correspond to a particular look associated with the subject (Tensemeyer in [0069] discloses, “the image projection system 106 selects a digital image having various stylistic properties (e.g., a painting effect, lighting effect, blending effect, color scheme) and/or various depicted attributes (e.g., a hairstyle, type of person, type of object, type of animal) as the initialization digital image”).
Summary of Citations (Tensemeyer)
Paragraph [0069]; “the image projection system 106 selects a digital image having various stylistic properties (e.g., a painting effect, lighting effect, blending effect, color scheme) and/or various depicted attributes (e.g., a hairstyle, type of person, type of object, type of animal) as the initialization digital image”.
Regarding claim 10, Tensemeyer in the combination discloses the method of claim 9, wherein the particular look corresponds to at least one of a hairstyle, a hair color, presence of facial hair, or absence of facial hair (Tensemeyer in [0069] discloses, “the image projection system 106 selects a digital image having various stylistic properties (e.g., a painting effect, lighting effect, blending effect, color scheme) and/or various depicted attributes (e.g., a hairstyle, type of person, type of object, type of animal) as the initialization digital image”).
Summary of Citations (Tensemeyer)
Paragraph [0069]; “the image projection system 106 selects a digital image having various stylistic properties (e.g., a painting effect, lighting effect, blending effect, color scheme) and/or various depicted attributes (e.g., a hairstyle, type of person, type of object, type of animal) as the initialization digital image”.
Regarding claim 11, Zhang in the combination discloses the method of claim 1, further comprising tuning the generative model using a (Zhang in [0023] discloses, “Fine-tuning the generative model refers to adjusting parameters (e.g., weights) of the generative model so that the generative model generates an image from the final latent and class vectors that more closely matches the target image”).
Tensemeyer further discloses subset of the set of images (Tensemeyer in [0098] discloses, “in some instances, the image projection system 106 utilizes another digital image (e.g., randomly selected, user selected) from the digital image batch 502 to generate the learned-initialization-latent vector ZINIT”).
Summary of Citations (Tensemeyer)
Paragraph [0098]; “in some instances, the image projection system 106 utilizes another digital image (e.g., randomly selected, user selected) from the digital image batch 502 to generate the learned-initialization-latent vector ZINIT”.
Summary of Citations (Zhang)
Paragraph [0023]; “Fine-tuning the generative model refers to adjusting parameters (e.g., weights) of the generative model so that the generative model generates an image from the final latent and class vectors that more closely matches the target image”.
Regarding claim 12, Zhang in the combination discloses the method of claim 11, wherein the tuning includes modifying one or more parameters of the generative model based on certain loss values (Zhang [0023] discloses, “After the loss condition is satisfied, the latent and class vectors that resulted in the loss condition being satisfied, also referred to as the final latent and class vectors, are used to fine-tune the generative model. Fine-tuning the generative model refers to adjusting parameters (e.g., weights) of the generative model so that the generative model generates an image from the final latent and class vectors that more closely matches the target image”).
Summary of Citations (Zhang)
Paragraph [0023]; “After the loss condition is satisfied, the latent and class vectors that resulted in the loss condition being satisfied, also referred to as the final latent and class vectors, are used to fine-tune the generative model. Fine-tuning the generative model refers to adjusting parameters (e.g., weights) of the generative model so that the generative model generates an image from the final latent and class vectors that more closely matches the target image”.
Regarding claim 13, apparatus claim 13 corresponds to method claim 1. Therefore, the rejection analysis and motivation to combine of claim 1 is applicable to claim 13.
Regarding claim 16, apparatus claim 16 corresponds to method claim 4. Therefore, the rejection analysis and motivation to combine of claim 4 is applicable to claim 16.
Regarding claim 17, apparatus claim 17 corresponds to method claim 6. Therefore, the rejection analysis and motivation to combine of claim 6 is applicable to claim 17.
Regarding claim 18, apparatus claim 18 corresponds to method claim 7. Therefore, the rejection analysis and motivation to combine of claim 7 is applicable to claim 18.
Regarding claim 19, Tensemeyer in the combination discloses the processing system of claim 13, wherein the one or more processors are further configured to tailor the set of images to either: correspond to a particular phase of life associated with the subject; or correspond to a particular look associated with the subject (Tensemeyer in [0069] discloses, “the image projection system 106 selects a digital image having various stylistic properties (e.g., a painting effect, lighting effect, blending effect, color scheme) and/or various depicted attributes (e.g., a hairstyle, type of person, type of object, type of animal) as the initialization digital image”).
Summary of Citations (Tensemeyer)
Paragraph [0069]; “the image projection system 106 selects a digital image having various stylistic properties (e.g., a painting effect, lighting effect, blending effect, color scheme) and/or various depicted attributes (e.g., a hairstyle, type of person, type of object, type of animal) as the initialization digital image”.
Regarding claim 20, apparatus claim 20 corresponds to method claim 11. Therefore, the rejection analysis and motivation to combine of claim 11 is applicable to claim 20.
Claims 2, 3, 14 and 15 are rejected under 35 U.S.C 103 as being unpatentable over Tensemeyer) in view of Zhang and Banerjee US Patent Application No. US-20230109108-A1 (hereinafter Banerjee).
Regarding claim 2, Tensemeyer in the combination discloses the method of claim 1, wherein the personalized prior is based on (Tensemeyer in [0097] discloses “generates learned-latent vector Z.sub.2” (given code) through learned-latent vector Z.sub.N for digital images 2 to N from the digital image (set of image), “the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N”).
Tensemeyer and Zhang in the combination doesn’t disclose about the following limitation as further recited in the claim.
Banerjee discloses convex hull (Banerjee in [0323] discloses, “In one example, the region generation engine 316 can generate region parameters 318 that define an (approximation of a) convex hull of the set of embeddings in the latent space”).
It would have been obvious to one of ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Banerjee into the system of Tensemeyer in view of Zhang because it would allow the system to generate image that are more likely to reflect the subject’s identified features.
Summary of Citations (Banerjee)
Paragraph [0323]; “In one example, the region generation engine 316 can generate region parameters 318 that define an (approximation of a) convex hull of the set of embeddings in the latent space”.
Summary of Citations (Tensemeyer)
Paragraph [0097]; “the image projection system 106 also utilizes the learned-initialization-latent vector Z.sub.INIT to generate learned-latent vectors that, when processed by an image-generating-neural network, convert into reconstructed versions of each of the remaining digital images from the digital image batch 502 (e.g., a learned-latent vector Z.sub.N for digital image N). Indeed, in one or more embodiments, the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N)”.
Regarding claim 3, Tensemeyer in the combination discloses the method of claim 1, wherein the personalized prior corresponds to a(Tensemeyer in [0097] discloses “generates learned-latent vector Z.sub.2” (given code) through learned-latent vector Z.sub.N for digital images 2 to N from the digital image (set of image), “the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N”).
Tensemeyer and Zhang in the combination doesn’t disclose about the following limitation as further recited in the claim.
Banerjee discloses subset of elements of a convex hull (Banerjee in [0139] discloses about convex hull, “the region of the latent space that encloses the set of embeddings in the latent space is a convex hull of the set of embeddings in the latent space”. Furthermore, Banerjee in [0140] discloses about combining the selected subset directly to the convex hull, “the set of embeddings, to identify a proper subset of the embeddings in the set of embeddings as being archetype embeddings comprises: determining a set of vertices of the region enclosing the set of embeddings in the latent space”).
Summary of Citations (Banerjee)
Paragraph [0139]; “the region of the latent space that encloses the set of embeddings in the latent space is a convex hull of the set of embeddings in the latent space”.
Paragraph [0140]; “the set of embeddings, to identify a proper subset of the embeddings in the set of embeddings as being archetype embeddings comprises: determining a set of vertices of the region enclosing the set of embeddings in the latent space”.
Summary of Citations (Tensemeyer)
Paragraph [0097]; “the image projection system 106 also utilizes the learned-initialization-latent vector Z.sub.INIT to generate learned-latent vectors that, when processed by an image-generating-neural network, convert into reconstructed versions of each of the remaining digital images from the digital image batch 502 (e.g., a learned-latent vector Z.sub.N for digital image N). Indeed, in one or more embodiments, the image projection system 106 generates learned-latent vector Z.sub.2 through learned-latent vector Z.sub.N for digital images 2 to N from the digital image batch 502 by utilizing the learned-initialization-latent vector Z.sub.INIT as a learned prior (e.g., the initial latent vector in each of the projection of digital images 2 to N)”.
Regarding claim 14, apparatus claim 14 corresponds to method claim 2. Therefore, the rejection analysis and motivation to combine of claim 2 is applicable to claim 14.
Regarding claim 15, apparatus claim 15 corresponds to method claim 3. Therefore, the rejection analysis and motivation to combine of claim 3 is applicable to claim 15.
Claim 5 is rejected under 35 U.S.C 103 as being unpatentable over Tensemeyer in view of Zhang and Li US Patent Application No. US-20200175757-A1 (hereinafter Li).
Regarding claim 5, Tensemeyer in the combination discloses the method of claim 4, wherein generating the set of candidate images comprises: generating the set of candidate images using the corresponding codes (Tensemeyer in [0125] discloses, “generating reconstructed digital images utilizing the image-generating-neural network based on the modified versions of the learned-initialization-latent vector until reconstructing a version of the second digital image”).
Tensemeyer and Zhang in the combination doesn’t disclose about the following limitation as further recited in the claim.
Li discloses generating different candidate coefficient sets (Li in [0051] discloses about coefficient sets, “512-dimensional PCA coefficients y may be used as a compact feature representation of the feasible space of 3D hairstyles”), the different candidate coefficient sets each having corresponding codes (Li in [0038] discloses, “Processing may be performed through the hair coefficient block 324 and the PCA.sup.−1 block 326 to latent code z 328”).
It would have been obvious to one of ordinary skill in art before the effective filling date of the claimed invention to integrate the technique of Li into the system of Tensemeyer in view of Zhang because it would allow the system to search through multiple variations of the subjects appearance within the personalized prior.
Summary of Citations (Li)
Paragraph [0038]; “Processing may be performed through the hair coefficient block 324 and the PCA.sup.−1 block 326 to latent code z 328”.
Paragraph [0051]; “512-dimensional PCA coefficients y may be used as a compact feature representation of the feasible space of 3D hairstyles”.
Summary of Citations (Tensemeyer)
Paragraph [0125]; “generating reconstructed digital images utilizing the image-generating-neural network based on the modified versions of the learned-initialization-latent vector until reconstructing a version of the second digital image”.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to ZAID MUHAMMAD SALEH whose telephone number is (703)756-1684.
The examiner can normally be reached M-F 8 am - 5 pm ET. 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, Vu Le can be
reached on (571)272-7332. 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.
/ZAID MUHAMMAD SALEH/
Examiner, Art Unit 2668
08/18/2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights