ATTENTION CONTRAST-AND-COMPLETE FOR INITIAL NOISE OPTIMIZATION IN TEXT-TO-IMAGE SYNTHESIS

Application No. 18/950,718

• Filed: Nov 18, 2024
• Examiner: BROWN, SHEREE N
• Art Unit: 2612
• Tech Center: 2600 — Communications
• Assignee: Adobe Inc.
• OA Round: 1 (Non-Final)

Office Action

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.:18/950,718 filed on 11/18/2024.
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 11/18/2024 is being considered by the examiner. A signed IDS is hereby attached.
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) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over YAMADA, US20250104291 in view of Weber, US20080069445.
Claim 1:
YAMADA a method (See YAMADA Abstract). YAMADA failed to explicitly disclose a second location. Weber discloses this feature in paragraph 0271. 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 YAMADA by the teachings of Weber to enable improved image processing systems, as taught Weber by including locations, more effectively (See Weber Paragraph 0001). Additionally, 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 generation.
As modified:
The combination of YAMADA and Weber discloses the following:
obtaining an input prompt describing a first element and a second element (See YAMADA Figure 10, Item s1010; Paragraph 0084);
generating, using an image generation model, an intermediate output based on the input prompt (See YAMADA Figure 10, Item s1045; Paragraph 0106);
optimizing the intermediate output based on an attention contrast loss (See YAMADA Paragraphs 0044-0046; 0076-0078) to obtain an optimized intermediate output (See YAMADA Figure 10, Item s1055; Paragraph 0108), wherein the optimized intermediate output represents the first element at a first location and the second element at a second location (See Weber Paragraph 0271);
and generating, using the image generation model, a synthetic image based on the optimized intermediate output (See YAMADA Figure 10, Item s1055; Paragraph 0108), wherein the synthetic image depicts the first element at the first location and the second element at the second location (See Weber Paragraph 0271).
Claim 2:
The combination of YAMADA and Weber discloses encoding the input prompt to obtain a text embedding, wherein the intermediate output is based on the text embedding (See YAMADA Paragraphs 0043; 0091; 0096; 0098; 0153).
Claim 3:
The combination of YAMADA and Weber discloses wherein optimizing the intermediate output comprises: updating a mean (See YAMADA Paragraphs 0044-0046) and a covariance of the intermediate output (See Weber Paragraph 0177).
Claim 4:
The combination of YAMADA and Weber discloses wherein optimizing the intermediate output comprises: generating a self-attention map for the first element (See YAMADA Paragraphs 0044-0046; 0076-0078); generating a cross-attention map between the first element and the second element (See YAMADA Paragraphs 0044-0046; 0076-0078); and computing an attention contrast term based on the self-attention map and the cross-attention map, wherein the attention contrast loss includes the attention contrast term (See YAMADA Paragraphs 0044-0046; 0076-0078).
Claim 5:
The combination of YAMADA and Weber discloses wherein optimizing the intermediate output comprises: generating a self-attention map for the first element (See YAMADA Paragraphs 0044-0046; 0076-0078); generating a cross-attention map between the first element and itself (See YAMADA Paragraphs 0044-0046; 0076-0078); and computing an attention complete term based on the self-attention map and the cross-attention map, wherein the attention contrast loss includes the attention complete term (See YAMADA Paragraphs 0044-0046; 0076-0078).
Claim 6:
The combination of YAMADA and Weber discloses wherein optimizing the intermediate output comprises: computing a distribution divergence term, wherein the attention contrast loss includes the distribution divergence term (See Weber Paragraph 0177).
Claim 7:
The combination of YAMADA and Weber discloses wherein generating the synthetic image comprises: denoising the intermediate output (See YAMADA Paragraphs 0052-0054; 0060-0061).
Claims 8-14:
Claims 8-14 are rejected on the same basis as claims 1-7.
Claim 15
Claim 15 is rejected on the same basis as claim 1.
Claim 16:
The combination of YAMADA and Weber discloses wherein: the image generation model includes an attention layer, and wherein the attention contrast loss is based on an output of the attention layer (See YAMADA Paragraph 0077).
Claim 17:
The combination of YAMADA and Weber discloses wherein: the image generation model includes a latent diffusion model (See YAMADA Paragraph 0060).
Claims 18-20:
Claims 18-20 are rejected on the same basis as claims 2-5.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHEREE N BROWN whose telephone number is [phone]. 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 [phone]. 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 June 1, 2026

Prosecution Timeline

• Nov 18, 2024: Application Filed
• Jun 04, 2026: Non-Final Rejection mailed — §103 (current)