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 .
Application Status
This office action is responsive to the Application No.:18/958,104, filed on 11/25/2024.
Claims 1-20 are pending and presented for examination.
This action has been made NON-FINAL.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/25/2024 is being considered by the examiner. A signed IDS is hereby attached.
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.
Claim(s) 1-15 and 17-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by AZARIAN YAZDI, US 20250166236.
Claim 1:
AZARIAN YAZDI discloses a method for image processing (See AZARIAN YAZDI Abstract), the method comprising:
obtaining a guidance condition representing an image element (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089);
computing a conditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052) based the guidance condition and an unconditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052) independent of the guidance condition (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089);
computing an adaptive guidance strength based on the guidance condition (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089);
combining the conditioned tensor and the unconditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052) based on the adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) to obtain a scoring tensor (See AZARIAN YAZDI Paragraphs 0050-0052);
and generating, using an image generation model, a synthetic image depicting the image element (See AZARIAN YAZDI Figure 10, Item 1010; Figure 11, Item 1108; Paragraphs 0108-0110; 0120) based on the scoring tensor (See AZARIAN YAZDI Paragraphs 0050-0052).
Claim 2:
AZARIAN YAZDI discloses wherein: the adaptive guidance strength varies based on pixel location (See AZARIAN YAZDI “pixel space” in Paragraph 0038).
Claim 3:
AZARIAN YAZDI discloses wherein computing the adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) comprises: computing a similarity (See AZARIAN YAZDI Paragraphs 0057; 0086) between the conditioned tensor and the unconditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052), wherein the adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) is based on the similarity (See AZARIAN YAZDI Paragraphs 0057; 0086).
Claim 4:
AZARIAN YAZDI discloses wherein computing the adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) comprises: computing an attention map (See AZARIAN YAZDI Paragraphs 0005; 0024-0027; 0029-0030; 0047-0050) based on the guidance condition (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089), wherein the adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) is based on the attention map (See AZARIAN YAZDI Paragraphs 0005; 0024-0027; 0029-0030; 0047-0050).
Claim 5:
AZARIAN YAZDI discloses wherein computing the adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) comprises: determining an adaptive schedule, wherein adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) is further based on the adaptive schedule (See AZARIAN YAZDI Paragraph 0055).
Claim 6:
AZARIAN YAZDI discloses wherein generating the synthetic image (See AZARIAN YAZDI Figure 10, Item 1010; Figure 11, Item 1108; Paragraphs 0108-0110; 0120) comprises: obtaining a noise map (See AZARIAN YAZDI Paragraph 0028; 0038); and denoising the noise map (See AZARIAN YAZDI Paragraph 0028; 0038) based on the scoring tensor (See AZARIAN YAZDI Paragraphs 0050-0052).
Claim 7:
AZARIAN YAZDI discloses wherein generating the synthetic image (See AZARIAN YAZDI Figure 10, Item 1010; Figure 11, Item 1108; Paragraphs 0108-0110; 0120) comprises: iteratively updating the adaptive guidance strength at a diffusion timestep (See AZARIAN YAZDI Paragraphs 0034; 0038); and computing the scoring tensor (See AZARIAN YAZDI Paragraphs 0050-0052) for the diffusion timestep (See AZARIAN YAZDI Paragraphs 0034; 0038) based on the updated adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089).
Claim 8:
Claim 8 is rejected on the same basis as claim 1.
Claim 9:
AZARIAN YAZDI discloses obtaining a text prompt describing the image element (See AZARIAN YAZDI Paragraphs 0033; 0036-0038; 0041-0043); and encoding the text prompt to obtain the guidance condition (See AZARIAN YAZDI Paragraphs 0033; 0036-0038; 0041-0043).
Claims 10-14:
Claims 10-14 are rejected on the same basis as claims 3-7.
Claim 15:
AZARIAN YAZDI discloses a system (See AZARIAN YAZDI Abstract) comprising:
a memory component (See AZARIAN YAZDI Figures 12 and 13; Paragraphs 0126-0132);
a processing device coupled to the memory component (See AZARIAN YAZDI Figures 12 and 13; Paragraphs 0126-0132);
and an image generation model (See Figure 8; Paragraphs 0001-0003; 0023-0030) comprising parameters stored in the memory component (See AZARIAN YAZDI Figures 12 and 13; Paragraphs 0126-0132) and configured to compute an adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089) for combining a conditioned tensor and an unconditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052) that is different for different image locations and to generate a synthetic image (See AZARIAN YAZDI Figure 10, Item 1010; Figure 11, Item 1108; Paragraphs 0108-0110; 0120) based on the adaptive guidance strength (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089).
Claim 17:
AZARIAN YAZDI discloses wherein computing the adaptive guidance strength comprises: computing the conditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052) based on a guidance condition (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089); computing the unconditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052) independent of the guidance condition (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059; 0089); and computing a similarity between the conditioned tensor and the unconditioned tensor (See AZARIAN YAZDI Paragraphs 0050-0052), wherein the adaptive guidance strength is based on the similarity (See AZARIAN YAZDI Paragraph 0057-0086).
Claims 18 and 19:
Claims 18 and 19 are rejected on the same basis as claims 4 and 5.Claim 20:
AZARIAN YAZDI discloses a text encoder configured to encode a text prompt to obtain a guidance condition (See AZARIAN YAZDI Paragraphs 0033; 0036-0038; 0041-0043), wherein the adaptive guidance strength determines a strength of the guidance condition (See AZARIAN YAZDI Paragraphs 0048; 0050; 0059).
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.
Claim(s) 16 is rejected under 35 U.S.C. 103 as being unpatentable over AZARIAN YAZDI, US 20250166236 in view of Chemerys, US 20240394933.
Claim 16:
AZARIAN YAZDI failed to disclose a classifier free guidance (CFG) diffusion model. However, Chemerys discloses this feature in Paragraphs 0103; 0107; 0114-0118; 0194-0196; 0203-0205. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified AZARIAN YAZDI by the teachings of Chemerys to enable improved image processing by incorporating diffusion models, as taught by Chemerys, more effectively. In addition, both of the references teach features that are directed to analogous art and they are directed to the same field of endeavor, such as, image processing. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of AZARIAN YAZDI and Chemerys discloses the following:
wherein the image generation model comprises a classifier free guidance (CFG) diffusion model (See Chemerys Paragraphs 0103; 0107; 0114-0118; 0194-0196; 0203-0205).
Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 12651313 discloses a system for image generation include obtaining an input image having a first resolution, where the input image includes random noise, and generating a low-resolution image based on the input image, where the low-resolution image has the first resolution.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHEREE N BROWN whose telephone number is (571)272-4229. The examiner can normally be reached M-F 5:30-2:00 PM 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, SAID BROOME can be reached at (571) 272-2931. 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.
/SHEREE N BROWN/Primary Examiner, Art Unit 2612 July 6, 2026
Prosecution Insights