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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 8/27/2025 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
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 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 and 21-23 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Brooks et al (“InstructPix2Pix: Learning to Follow Image Editing Instructions”, arXiv:2211.09800, https://doi.org/10.48550/arXiv.2211.09800, 11/17/2023, pages 1-15, retrieved from the Internet on 7/15/2026).
Regarding claim 1, Brooks discloses a method performed by one or more computers, the method comprising:
receiving an input image (Input in figs. 5-6);
obtaining a restoration prompt that specifies a restoration procedure to be applied to the input image (Edit instruction in Table 1; figs. 4-6; section 3.1, );
initializing a representation of a restored image (fig. 12; section 3.2, We therefore initialize the weights of our model with a pretrained Stable Diffusion checkpoint, leveraging its vast text-to-image generation capabilities. All available weights of the diffusion model are initialized from the pretrained checkpoints, and weights that operate on the newly added input channels are initialized to zero);
updating the representation of the restored image to generate a final representation of the restored image, the updating comprising, at each of a plurality of sampling iterations (section 3.2, Diffusion models learn to generate data samples
through a sequence of denoising autoencoders; section A.2, We generate images with 100 denoising steps using an Euler ancestral sampler with denoising variance schedule):
generating a denoising output for the sampling iteration (Equation 1; section 3.2), comprising processing a first diffusion input for the sampling iteration that comprises (i) the representation of the restored image (section 3.2, To support image conditioning, we add additional input channels to the first convolutional layer, concatenating zt and E(cI)), (ii) a representation of the input image (Equation 1; input image cI), and (iii) a representation of the restoration prompt (Equation 1, text instruction conditioning cT) using a diffusion neural network to generate a first denoising output (Equations 2-3; section 3.2.1, The implementation of classifier-free guidance involves jointly training the diffusion model for conditional and unconditional denoising); and
updating the representation of the restored image using the denoising output (section 3.2, Diffusion models learn to generate data samples through a sequence of denoising autoencoders; section A.2, We generate images with 100 denoising steps using an Euler ancestral sampler with denoising variance schedule); and
generating a restored image from the final representation of the restored image (section 3.2, Latent diffusion improves the efficiency and quality of diffusion models by operating in the latent space of a pretrained variational autoencoder with encoder E and decoder D. The output of decoder would be the restored image).
Regarding claim 6, Brooks discloses a method wherein the representation of the restored image and the representation of the input image are respective latent representations in a latent space (section 3.2).
Regarding claim 7, Brooks discloses a method further comprising: generating the representation of the input image by processing the input image using an image encoder neural network (section 3.2).
Regarding claim 8, Brooks discloses a method wherein generating a restored image from the final representation of the restored image comprises:
processing the final representation of the restored image using an image decoder neural network to generate the restored image (section 3.2).
Regarding claim 21, Brooks discloses a method wherein generating a denoising output for the sampling iteration comprises:
processing a second diffusion input for the sampling iteration that comprises the representation of the restored image using the diffusional neural network to generate a second denoising output (section 3.2-3.2.1, score network); and
generating the denoising output using the first denoising output and the second denoising output (Equation 3).
Regarding claim 22, claim recites similar subject matter as claim 1 and is rejected for the same reasons as stated above.
Regarding claim 23, claim recites similar subject matter as claim 1 and is rejected for the same reasons as stated above.
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.
Claim(s) 2-3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brooks et al (“InstructPix2Pix: Learning to Follow Image Editing Instructions”, arXiv:2211.09800, https://doi.org/10.48550/arXiv.2211.09800, 11/17/2023, pages 1-15, retrieved from the Internet on 7/15/2026) in view of Geng et al (“InstructDiffusion: A generalist Modeling Interface for Vision Tasks”, arXiv:2309.03895, https://doi.org/10.48550/arXiv.2309.03895, 9/7/2023, pages 1-16, retrieved from the Internet on 7/15/2026).
Regarding claim 2, Brooks fails to teach a method wherein the restoration prompt specifies that the restoration procedure removes all degradation in the input image.
However Geng teaches wherein a restoration prompt specifies that the restoration procedure removes all degradation in the input image (fig. 5, “Purify this photo by removing noise”. If noise is the only degradation, all the degradation would be removed. Furthermore, it would be obvious to combine the prompts).
Therefore taking the combined teachings of Brooks and Geng as a whole, it would have been obvious to one of ordinary skill in the art at the time the invention was filed to incorporate the steps of Geng into the method of Brooks. The motivation to combine Geng and Brooks would be to solve the problem of quantization error (section 1 of Geng).
Regarding claim 3, Brooks fails to teach a method wherein the restoration prompt specifies that the restoration procedure removes one or more specific types of degradation from the input image.
However Geng teaches wherein a restoration prompt specifies that the restoration procedure removes one or more specific types of degradation from the input image (fig. 5, “Sharpen this blurry image”, “Purify this photo by removing noise”).
Therefore taking the combined teachings of Brooks and Geng as a whole, it would have been obvious to one of ordinary skill in the art at the time the invention was filed to incorporate the steps of Geng into the method of Brooks. The motivation to combine Geng and Brooks would be to solve the problem of quantization error (section 1 of Geng).
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brooks et al (“InstructPix2Pix: Learning to Follow Image Editing Instructions”, arXiv:2211.09800, https://doi.org/10.48550/arXiv.2211.09800, 11/17/2023, pages 1-15, retrieved from the Internet on 7/15/2026) and Geng et al (“InstructDiffusion: A generalist Modeling Interface for Vision Tasks”, arXiv:2309.03895, https://doi.org/10.48550/arXiv.2309.03895, 9/7/2023, pages 1-16, retrieved from the Internet on 7/15/2026) in view of Kwon et al (US20220138924).
Regarding claim 4, the modified method of Brooks fails to teach a method wherein the restoration prompt includes one or more numeric values that specify an intensity of the restoration procedure.
However Kwon teaches wherein a restoration prompt (para. [0055], it would be obvious for the tuning condition to be a prompt) includes one or more numeric values that specify an intensity of the restoration procedure (para. [0054]).
Therefore taking the combined teachings of modified Brooks and Kwon as a whole, it would have been obvious to one of ordinary skill in the art at the time the invention was filed to incorporate the steps of Kwon into the method of modified Brooks. The motivation to combine Kwon and modified Brooks would be to allow control based on a user’s preference (para. [0047] of Kwon), thus increasing a user’s experience.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brooks et al (“InstructPix2Pix: Learning to Follow Image Editing Instructions”, arXiv:2211.09800, https://doi.org/10.48550/arXiv.2211.09800, 11/17/2023, pages 1-15, retrieved from the Internet on 7/15/2026) in view of Rombach et al ("High-resolution image synthesis with latent diffusion models." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022, pages 10684-10695, retrieved from the Internet on 7/16/2026).
Regarding claim 5, Brooks fails to teach a method further comprising:
generating the representation of the restoration prompt by processing the restoration prompt using a first text embedding neural network.
However Rombach teaches generating a representation of a restoration prompt by processing the restoration prompt using a first text embedding neural network (section 3.3, To pre-process y from various modalities (such as language prompts) we introduce a domain specific encoder τθ that projects y to an intermediate representation τθ(y) ∈ RM×dτ , which is then mapped to the intermediate layers of the UNet; section 4.3.1).
Therefore taking the combined teachings of Brooks and Rombach as a whole, it would have been obvious to one of ordinary skill in the art at the time the invention was filed to incorporate the steps of Rombach into the method of Brooks. The motivation to combine Rombach and Brooks would be to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity while significantly reducing computational requirements (abstract of Rombach).
Claim(s) 9-10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brooks et al (“InstructPix2Pix: Learning to Follow Image Editing Instructions”, arXiv:2211.09800, https://doi.org/10.48550/arXiv.2211.09800, 11/17/2023, pages 1-15, retrieved from the Internet on 7/15/2026) in view of Wu et al (“SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution”, arXiv:2311.16518, https://doi.org/10.48550/arXiv.2311.16518, 11/27/2023, pages 1-12, retrieved from the Internet on 7/16/2026).
Regarding claim 9, Brooks fails to teach a method further comprising:
receiving a semantic prompt characterizing one or more semantic properties of the restored image, wherein the first diffusion input further comprises a representation of the semantic prompt.
However Wu teaches receiving a semantic prompt characterizing one or more semantic properties of the restored image (abstract; section 3.3), wherein the first diffusion input further comprises a representation of the semantic prompt (Equation 2).
Therefore taking the combined teachings of Brooks and Wu as a whole, it would have been obvious to one of ordinary skill in the art at the time the invention was filed to incorporate the steps of Wu into the method of Brooks. The motivation to combine Wu and Brooks would be to generate detailed and semantically accurate results (abstract of Wu).
Regarding claim 10, the modified method of Brooks teaches a method further comprising:
generating the representation of the semantic prompt by processing the semantic prompt using a second text embedding neural network (fig. 2 (c) and sections 3.2-3.3 of Wu).
Related Art
Park et al (US20250124544) - see para. [0078]-[0079], [0088]
Vecchio et al (US20250069373) – see fig. 3, para. [0066]-[0067], [0073]
Allowable Subject Matter
Claims 11-20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEON VIET Q NGUYEN whose telephone number is (571)270-1185. The examiner can normally be reached Mon-Fri 11AM-7PM.
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, Gregory Morse can be reached at 571-272-3838. 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.
/LEON VIET Q NGUYEN/ Primary Examiner, Art Unit 2663
Prosecution Insights