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 .
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-3, 5-7, 9-11, 13, 15, 21-23, and 25 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Kanazawa et al, (U.S. Patent Application Publication No. 2023/0342890), referred herein as Kanazawa.
Regarding claim 1, Kanazawa teaches at least one processor, comprising: processing circuitry to (fig 1A; paragraphs 95 and 101):
generate, using at least one machine learning model, a first image corresponding to a foreground of an input image (figs 2A and 2B, input image 206 and first images 210 or 222; paragraph 82, lines 1-9; paragraph 117, lines 8-17; paragraph 127; paragraph 129, lines 1-10; an image corresponding to a foreground of an input image is generated using a machine learning model);
generate, using the at least one machine learning model, one or more second images corresponding to a background of the input image (figs 2A and 2B, input image 206 and second images 214 or 224; paragraph 82, lines 1-9; paragraph 117, lines 8-17; paragraph 128, lines 1-11; paragraph 130; an image corresponding to a background of an input image is generated using a machine learning model); and
cause a display of an animated effect generated using the first image and at least one of the one or more second images (paragraphs 165 and 166; paragraph 167, lines 1-6; an animated effect is generated using the first and second images).
Regarding claim 2, Kanazawa teaches the at least one processor of claim 1, wherein the input image is a two-dimensional image (figs 2A and 2B, two-dimensional input image 206; paragraph 31; pixel images are two-dimensional).
Regarding claim 3, Kanazawa teaches the at least one processor of claim 1, wherein the processing circuitry is further to: generate a mask associated with the foreground of the first image; and generate one or more replacement pixels for the mask (paragraph 127; paragraph 128, lines 1-11; paragraph 130) using one or more trained neural networks (paragraphs 96, 103, and 104).
Regarding claim 5, Kanazawa teaches the at least one processor of claim 1, wherein the processing circuitry is further to: determine one or more parameters associated with a user; and select the animated effect based on the one or more parameters (paragraph 53, lines 1-13; paragraph 54, lines 1-3; paragraphs 74 and 75).
Regarding claim 6, Kanazawa teaches the at least one processor of claim 1, wherein the processing circuitry is further to: identify one or more components associated with the foreground; and extract, from the input image, the one or more components (figs 2A and 2B; paragraph 127; paragraph 128, lines 1-11; paragraph 129, lines 1-10; paragraph 130; any one of the extracted foreground components).
Regarding claim 7, Kanazawa teaches the at least one processor of claim 6, wherein the processing circuitry is further to: generate at least one second image of the one or more second images including one or more second objects related to the one or more components in the foreground (figs 2A and 2B; paragraph 127; paragraph 128, lines 1-11; paragraph 129, lines 1-10; paragraph 130; the second images are related to the foreground components).
Regarding claim 9, Kanazawa teaches the at least one processor of claim 1, wherein the at least one processor is comprised in at least one of: a system for performing simulation operations; a system for performing simulation operations to test or validate autonomous machine applications; a system for performing digital twin operations; a system for performing light transport simulation; a system for rendering graphical output; a system for performing deep learning operations; a system implemented using an edge device; a system for generating or presenting virtual reality (VR) content; a system for generating or presenting augmented reality (AR) content; a system for generating or presenting mixed reality (MR) content; a system incorporating one or more Virtual Machines (VMs);a system for performing operations for a conversational AI application; a system for performing operations for a generative AI application; a system for performing operations using a language model; a system for performing one or more operations using a large language model (LLM);a system for performing one or more operations using a vision language model (VLM);a system implemented at least partially in a data center; a system implemented using a robot; a system for performing hardware testing using simulation; a system for performing one or more generative content operations using a language model; a system for synthetic data generation; a collaborative content creation platform for 3D assets; or a system implemented at least partially using cloud computing resources (paragraphs 62 and 71; paragraph 114; paragraphs 128 and 130; paragraph 167, lines 1-6).
Regarding claim 10, Kanazawa teaches a computer-implemented method, comprising: extracting one or more foreground components identified in an input image, and generating, based on the input image, a first image including at least a portion of the one or more foreground components (figs 2A and 2B, input image 206, first images 210 or 222; paragraph 82, lines 1-9; paragraph 127, lines 1-9; paragraph 129, lines 1-10; paragraph 130, lines 1-2; foreground components are extracted from an input image, and a first image is generated based on at least a portion of the components);
determining a mask region associated with the one or more foreground components in the input image, generating one or more replacement pixels for the mask region, and generating, based on the input image, at least one second image including the one or more replacement pixels in place of the mask region (figs 2A and 2B, input image 206, second images 214 or 224; paragraph 82, lines 1-9; paragraph 128, lines 1-11; paragraph 130; a mask region is determined that is associated with the foreground components, replacement pixels are generated for the mask, and a second image is generated that includes the replacement pixels); and
generating an animation using the first image and a particular second image of the at least one second image (paragraphs 165 and 166; paragraph 167, lines 1-6; an animation is generated using the first and second images).
Regarding claim 11, Kanazawa teaches the computer-implemented method of claim 10, further comprising: identifying the one or more foreground components in the input image, based on a context of the input image (figs 2A and 2B, input image 206, first images 210 or 222; paragraph 82, lines 1-9; paragraph 127, lines 1-9; paragraph 129, lines 1-10; paragraph 130, lines 1-2).
Regarding claim 13, Kanazawa teaches the computer-implemented method of claim 10, wherein one or more of the input image, the first image, and the at least one second image are two-dimensional images (figs 2A and 2B, two-dimensional images 206, 210, 214, 222, or 224; paragraph 31; pixel images are two-dimensional).
Regarding claim 15, Kanazawa teaches the computer-implemented method of claim 10, wherein the one or more replacement pixels are generated using a trained neural network, and further comprising: receiving one or more prompts associated with the one or more replacement pixels (paragraphs 96, 103, and 104; paragraph 114; paragraph 128, lines 1-11; paragraph 130).
Regarding claim 21, Kanazawa teaches a system, comprising (fig 1A):
one or more processors to generate an animated effect using a generated first image and one or more generated second images (figs 2A and 2B; paragraphs 166 and 167; an animated effect is generated using a plurality of generated images),
the generated first image corresponding to a foreground of an input image and the one or more generated second images corresponding to a background of the input image (figs 2A and 2B, input image 206, first images 210 or 222, second images 214 or 224; paragraph 82, lines 1-9; paragraph 117, lines 8-17; paragraphs 127 and 128; paragraphs 165 and 166; the first image corresponds to a foreground of the input image, the second images correspond to a background of the input image).
Regarding claims 22, 23, and 25, the limitations of these claims substantially correspond to the limitations of claims 2, 3, and 5, respectively; thus they are rejected on similar grounds as their corresponding claims.
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.
Claims 4, 8, 12, 14, and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Kanazawa, in view of Lwowski et al. (U.S. Patent Application Publication No. 2021/0201077), referred herein as Lwowski.
Regarding claim 4, Kanazawa teaches the at least one processor of claim 1, wherein the processing circuitry is further to: identify one or more regions of a particular second image of the one or more second images, and generate one or more pixels (paragraph 127; paragraph 128, lines 1-11; paragraph 130) using one or more trained neural networks (paragraphs 96, 103, and 104).
The masked silhouette regions described in Kanazawa have edges, and the pixel replacement filling in those regions would include filling in all the way to, and including, the borders of those regions. However, Kanazawa does not explicitly discuss identifying edge regions and generating border pixels.
However, in a similar field of endeavor, Lwowski teaches a system comprising circuitry configured to generate, using a neural network machine learning model, a first image corresponding to a foreground of an input image and one or more second images corresponding to a background of the input image, and cause a display of an image effect by compositing the first and second images (fig 2A; paragraph 67; paragraph 73, lines 1-9; paragraph 74, lines 1-10), and further configured to identify edge regions and generate border pixels (paragraph 86; paragraph 87, lines 12-22).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the edge identification and border pixel generation of Lwowski with the pixel replacement of Kanazawa because this helps produce finer edges, while accurately blending the fine edges to produce higher quality, more accurate foreground and background composite images, without increasing computational costs associated with the machine learning (see, for example, Lwowski, paragraph 7; paragraph 87, lines 22-31).
Regarding claim 8, Kanazawa teaches the at least one processor of claim 1, wherein the processing circuitry is further to: generate output data associated with the animated effect, the output data including at least one of: an effect, one or more effect parameters, or identifying information for the first image and at least one of the one or more second images (paragraph 40, the last 4 lines; paragraph 45, the last 16 lines; paragraphs 46 and 47).
Kanazawa teaches utilizing program files (see, for example, paragraph 110), and the output data may reasonably be interpreted as performing the functions of the claimed configuration file. However, Kanazawa does not explicitly discuss that the output data is a configuration file.
However, in a similar field of endeavor, Lwowski teaches a system comprising circuitry configured to generate, using a neural network machine learning model, a first image corresponding to a foreground of an input image and one or more second images corresponding to a background of the input image, and cause a display of an image effect by compositing the first and second images (fig 2A; paragraph 67; paragraph 73, lines 1-9; paragraph 74, lines 1-10), and further configured to generate and utilize a configuration file including effect parameters or identifying information (paragraph 96, lines 9-20).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the configuration file of Lwowski with the output data of Kanazawa because this helps the training of the machine learning models such that higher quality image output can be provided, while minimizing any potential increase in computational costs associated with the machine learning (see, for example, Lwowski, paragraph 7; paragraph 96, lines 1-16).
Regarding claim 12, Kanazawa teaches the computer-implemented method of claim 10, further comprising: determining one or more settings associated with a user request, and selecting at least one of the animation or properties of the animation, based on the one or more settings (paragraph 53, lines 1-13; paragraph 54, lines 1-3; paragraphs 74 and 75; paragraph 167).
Kanazawa does not explicitly teach that the user requests access to one or more resources.
However, in a similar field of endeavor, Lwowski teaches a method comprising generating, using a neural network machine learning model, a first image corresponding to a foreground of an input image and one or more second images corresponding to a background of the input image, and causing a display of an image effect by compositing the first and second images (fig 2A; paragraph 67; paragraph 73, lines 1-9; paragraph 74, lines 1-10), wherein a user requests access to one or more resources to determine settings and properties of the image processing (paragraph 71, lines 1-8; paragraph 72, lines 6-15).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the user access request of Lwowski with the user request of Kanazawa because this improves the security of the resources being processed by authorizing only those users who have proper access to the resources, which is particularly important in client-server architectures such as those in Kanazawa (see, for example Lwowski, paragraph 71, lines 1-8 and the last 5 lines; paragraph 72, lines 1-6 and the last 4 lines).
Regarding claim 14, Kanazawa teaches the computer-implemented method of claim 10, further comprising: identifying one or more regions of a specific second image of the at least one second image, generating one or more pixels of the specific second image, and generating, based on the input image, the particular second image including the one or more pixels (paragraph 127; paragraph 128, lines 1-11; paragraph 130).
The masked silhouette regions described in Kanazawa have edges, and the pixel replacement filling in those regions would include filling in all the way to, and including, the borders of those regions. However, Kanazawa does not explicitly discuss identifying edges and generating border pixels extending beyond the one or more edges.
However, in a similar field of endeavor, Lwowski teaches a method comprising generating, using a neural network machine learning model, a first image corresponding to a foreground of an input image and one or more second images corresponding to a background of the input image, and causing a display of an image effect by compositing the first and second images (fig 2A; paragraph 67; paragraph 73, lines 1-9; paragraph 74, lines 1-10), and further comprising identifying one or more edges and generating border pixels extending beyond the one or more edges (paragraph 86; paragraph 87, lines 12-22).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the edge identification and border pixel generation of Lwowski with the pixel replacement of Kanazawa because this helps produce finer edges, while accurately blending the fine edges to produce higher quality, more accurate foreground and background composite images, without increasing computational costs associated with the machine learning (see, for example, Lwowski, paragraph 7; paragraph 87, lines 22-31).
Regarding claim 24, the limitations of this claim substantially correspond to the limitations of claim 4; thus they are rejected on similar grounds.
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Criminisi (U.S. Patent Application Publication No. 2011/0293180); Foreground and background image segmentation.
Shen (U.S. Patent Application Publication No. 2018/0260668); Harmonizing composite images using deep learning.
Cohen (U.S. Patent Application Publication No. 2019/0196698); Removing and replacing objects in images according to a directed user conversation.
Wilson (U.S. Patent Application Publication No. 2020/0074642); Motion assisted image segmentation.
Villegas (U.S. Patent Application Publication No. 2023/0037591); Inserting three-dimensional objects into digital images with consistent lighting via global and local lighting information.
Nagata (U.S. Patent Application Publication No. 2024/0338928); Video processing apparatus, video processing method, and program.
Rai (U.S. Patent Application Publication No. 2023/0127525); Generating digital assets utilizing a content aware machine-learning model.
Assouline (U.S. Patent No. 11,880,947); Real-time upper-body garment exchange.
Springer (U.S. Patent Application Publication No. 2023/0316534); Virtual background partitioning.
Springer (U.S. Patent Application Publication No. 2023/0316533); Virtual background sharing.
Beggel (U.S. Patent No. 12,277,696); Data augmentation for domain generalization.
Aitbayev (U.S. Patent Application Publication No. 2023/0316666); Pixel depth determination for object.
Yu (U.S. Patent No. 12,347,116); Generating alpha mattes utilizing deep learning.
Bagnall (U.S. Patent Application Publication No. 2024/0362758); Generating and implementing semantic histories for editing digital images.
Soni (U.S. Patent Application Publication No. 2024/0256218); Modifying digital images using combinations of direct interactions with the digital images and context-informing speech input.
Bagnall (U.S. Patent Application Publication No. 2024/0361891); Implementing graphical user interfaces for viewing and interacting with semantic histories for editing digital images.
Singh (U.S. Patent Application Publication No. 2024/0403543); Document decomposition based on determined logical visual layering of document content.
Singh (U.S. Patent Application Publication No. 2025/0111520); Generating image object segmentations utilizing graph-cut partitioning in self-supervised object discovery.
Smith (U.S. Patent No. 12,299,858); Modifying digital images utilizing intent deterministic user interface tools.
Li (U.S. Patent Application Publication No. 2024/0233775); Augmented performance replacement in a short-form video.
Lungu-stan (U.S. Patent Application Publication No. 2025/0322495); Texture based consistency for generative ai assets, effects and animations.
Agarwal (U.S. Patent Application Publication No. 2025/0371753); Content aware background generation.
Fitzpatrick (U.S. Patent Application Publication No. 2025/0157092); Dynamic modification of video content.
Belskikh (U.S. Patent Application Publication No. 2025/0166264); Diffusion model multi-person image generation.
Jawade (U.S. Patent Application Publication No. 2025/0292368); Systems and methods for image compositing via machine learning.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID T WELCH whose telephone number is (571)270-5364. The examiner can normally be reached on Monday-Thursday, 8:30-5:30 EST, and alternate Fridays, 9:00-2:30 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 on 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.
DAVID T. WELCH
Primary Examiner
Art Unit 2613
/DAVID T WELCH/Primary Examiner, Art Unit 2613
Prosecution Insights