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 7/2/2025 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, 2, 8-11, 14, 15, and 20 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." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 6/17/2023, pages 18392-18402, retrieved from the Internet on 6/28/2026).
Regarding claim 1, Brooks discloses a computer-implemented method to train a diffusion model to perform visual editing of material properties (bottom right image in fig. 1; abstract, Our conditional diffusion model, InstructPix2Pix, is trained on our generated data, and generalizes to real images and user-written instructions at inference time; section 4, modifying material attributes), the method comprising:
obtaining, by a computing system comprising one or more computing devices, a pair of training images, wherein the pair of training images comprises a target image and a context image (section 3, we generate a paired training dataset of text editing instructions and images before/after the edit; section 3.1, generate a multi-modal training dataset containing text editing instructions and the corresponding images before and after the edit), wherein the target image and the context image each depict a shared object (fig. 2c), and wherein a material property of the shared object differs between the target image and the context image (fig. 2c);
adding, by the computing system, a set of noise to the target image to obtain a noised target image (section 3.2, For an image x, the diffusion process adds noise to the encoded latent z = E(x) producing a noisy latent zt where the noise level increases over timesteps t ∈ T);
processing, by the computing system, the noised target image with a denoising diffusion model that is conditioned on the context image to generate a denoising prediction (section 3.2, We learn a network ϵθ that predicts the noise added to the noisy latent zt given image conditioning cI and text instruction conditioning cT);
evaluating, by the computing system, a loss function that evaluates the denoising prediction relative to the set of noise (equation 1; section 3.2, latent diffusion objective); and
modifying, by the computing system, one or more values of one or more parameters of the denoising diffusion model based on the loss function (section 3.2, 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. We reuse the same text conditioning mechanism that was
originally intended for captions to instead take as input the text edit instruction cT).
Regarding claim 2, Brooks discloses a computer-implemented method wherein the denoising diffusion model is further conditioned on a textual prompt that indicates an edit to the material property (fig. 1, “Make his jacket out of leather”; fig. 2c, “convert to brick”; section 3.1, given a prompt describing an image, produce a text instruction describing a change to be made and a prompt describing the image after that change).
Regarding claim 8, Brooks discloses a computer-implemented method wherein the denoising diffusion model comprises a latent diffusion model (section 3.2, We base our model on Stable Diffusion, a large-scale text-to-image latent diffusion model) and the set of noise is added in a latent space (section 3.2, For an image x, the diffusion process adds noise to the encoded latent z = E(x)).
Regarding claim 9, Brooks discloses a computing system comprising:
one or more processors (processors are necessary in computing systems); and
one or more non-transitory computer-readable media (memory is necessary in computing systems) that collectively store:
a denoising diffusion model configured to perform visual edits (section 1, Using our generated paired data, we train a conditional diffusion model that, given an input image and a text instruction for how to edit it, generates the edited image) to a material property of an object depicted in a context image (fig. 2c; section 4, modifying material attributes);
instructions that, when executed by the computing system, cause the computing system to perform operations, the operations comprising:
receiving the context image (figs. 1 and 2c; section 1, input image);
processing an input with the denoising diffusion model to generate an edited image (section 1, Using our generated paired data, we train a conditional diffusion model that, given an input image and a text instruction for how to edit it, generates the edited image), wherein the denoising diffusion model is conditioned on the context image (section 3.2.1, For our task, the score network eθ(zt, cI , cT) has two conditionings: the input image cI and text instruction cT), and wherein the edited image depicts the object with a modified material property (figs. 1 and 2c); and
providing the edited image as an output (figs. 1 and 2c; section 1, forward pass).
Regarding claim 10, Brooks discloses a computing system wherein the denoising diffusion model has been trained according to the method of claim 1 (see the rejection of claim 1).
Regarding claim 11, Brooks discloses a computing system wherein the input comprises a noise input (section 3.2, For an image x, the diffusion process adds noise to the encoded latent z = E(x) producing a noisy latent zt where the noise level increases over timesteps t ∈ T) and one or both of:
a textual prompt that describes an edit to the material property (fig. 1, “Make his jacket out of leather”; fig. 2c, “convert to brick”; section 3.1, given a prompt describing an image, produce a text instruction describing a change to be made and a prompt describing the image after that change); and
a scalar edit value for the material property.
Regarding claim 14, the claim recites similar subject matter as claim 1 and is rejected for the same reasons as stated above.
Regarding claim 15, the claim recites similar subject matter as claim 2 and is rejected for the same reasons as stated above.
Regarding claim 20, the claim recites similar subject matter as claim 8 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) 3-5, 12, and 16-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brooks et al ("Instructpix2pix: Learning to follow image editing instructions” Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 6/17/2023, pages 18392-18402, retrieved from the Internet on 6/28/2026) in view of Subias et al ("In‐the‐wild material appearance editing using perceptual attributes." Computer Graphics Forum, 5/23/2023, Vol. 42. No. 2, pages 333-345, retrieved from the Internet on 6/29/2026).
Regarding claim 3, Brooks fails to teach a computer-implemented method wherein the denoising diffusion model is further conditioned on a scalar edit value for the material property, wherein the scalar edit value corresponds to the material property exhibited by the target image.
However Subias teaches wherein a model is further conditioned on a scalar edit value for a material property (section 3.1, Our goal is to generate an image y whose material appearance we want to edit from an input image x and a value attt ∈ [0,1] of the target high-level perceptual attribute to edit (e.g., glossy or metallic)), wherein the scalar edit value corresponds to the material property exhibited by a target image (section 3.1, For instance, more glossy if attt is closer to 1 and less if closer to 0).
Therefore taking the combined teachings of Brooks and Subias 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 Subias into the method of Brooks. The motivation to combine Subias and Brooks would be to preserve high-frequency details from an input image in an edited one (abstract of Subias).
Regarding claim 4, the modified method of Brooks teaches a computer-implemented method wherein the scalar edit value is provided to the denoising diffusion model in an additional input channel (section 3.2.1 of Brooks, guidance scale).
Regarding claim 5, Brooks fails to teach a computer-implemented method wherein the pair of training images were generated using a physically-based renderer, wherein the physically-based renderer comprises a shader, and wherein the shader was supplied with different values for the material property of the shared object when rendering the target image and the context image.
However Subias teaches wherein a pair of training images were generated using a physically-based renderer (abstract, To train our framework we leverage a dataset with pairs of synthetic images rendered with physically-based algorithms), wherein the physically-based renderer comprises a shader (section 5.5, We compare our results with physically-based rendering by varying the roughness parameter of the Principled BSDF), and wherein the shader was supplied with different values for the material property of the shared object when rendering the target image and the context image (section 4.1, In addition, our framework would learn to edit based on variations in a physical parameter (e.g., roughness) and not on variations
in our perception. Each scene is described by a set of high-level perceptual attributes(i.e., plastic, rubber, metallic, glossy, bright, rough, and the strength and sharpness of reflections)).
Therefore taking the combined teachings of Brooks and Subias 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 Subias into the method of Brooks. The motivation to combine Subias and Brooks would be to preserve high-frequency details from an input image in an edited one (abstract of Subias).
Regarding claim 12, the claim recites similar subject matter as claims 3 and 4 and is rejected for the same reasons as stated above.
Regarding claim 16, the claim recites similar subject matter as claim 3 and is rejected for the same reasons as stated above.
Regarding claim 17, the claim recites similar subject matter as claim 4 and is rejected for the same reasons as stated above.
Regarding claim 18, the claim recites similar subject matter as claim 5 and is rejected for the same reasons as stated above.
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brooks et al ("Instructpix2pix: Learning to follow image editing instructions” Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 6/17/2023, pages 18392-18402, retrieved from the Internet on 6/28/2026) and Subias et al ("In‐the‐wild material appearance editing using perceptual attributes." Computer Graphics Forum, 5/23/2023, Vol. 42. No. 2, pages 333-345, retrieved from the Internet on 6/29/2026) in view of Sheffield et al (US10235797).
Regarding claim 6, the modified method of Brooks fails to teach a computer-implemented method wherein the shader was supplied with a value of zero for the material property of the shared object when rendering the context image.
However Sheffield teaches supplying with a value of zero for a material property of a shared object (col. 5 lines 64-67) when rendering a context image (abstract).
Therefore taking the combined teachings of Brooks and Subias with Sheffield 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 Sheffield into the method of Brooks and Subias. The motivation to combine Sheffield, Subias and Brooks would be to ensures that results are accurate despite potential differences in visual material property values for a material (col. 19 lines 38-40 of Sheffield).
Claim(s) 7, 13, an 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Brooks et al ("Instructpix2pix: Learning to follow image editing instructions” Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 6/17/2023, pages 18392-18402, retrieved from the Internet on 6/28/2026) in view of Perroni-Scharf et al (US20230141395).
Regarding claim 7, Brooks fails to teach a computer-implemented method wherein the material property comprises one or more of roughness, metallic property, albedo, and transparency.
However Perroni-Scharf teaches wherein a material property comprises one or more of roughness (para. [0032], [0049]), metallic property (para. [0049]), albedo (para. [0032], [0049]), and transparency (para. [0049]).
Therefore taking the combined teachings of Brooks and Perroni-Scharf 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 Perroni-Scharf into the method of Brooks. The motivation to combine Perroni-Scharf and Brooks would be to flexibly, accurately, and efficiently generate synthesized digital images (para. [0002] of Perroni-Scharf).
Regarding claim 13, the claim recites similar subject matter as claim 7 and is rejected for the same reasons as stated above.
Regarding claim 19, the claim recites similar subject matter as claim 7 and is rejected for the same reasons as stated above.
Related Art
Ceylan Aksit et al (US20250111866) – see para. [0047], [0069]
Gadelha et al (US20250061650) – see para. [0022], [0056], [0075]
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