Office Action Predictor
Last updated: April 15, 2026
Application No. 18/528,352

ITEM RETRIEVAL USING GENERATIVE INPAINTING

Non-Final OA §103
Filed
Dec 04, 2023
Examiner
LU, ZHIYU
Art Unit
2665
Tech Center
2600 — Communications
Assignee
Adobe INC.
OA Round
2 (Non-Final)
49%
Grant Probability
Moderate
2-3
OA Rounds
3y 10m
To Grant
64%
With Interview

Examiner Intelligence

Grants 49% of resolved cases
49%
Career Allow Rate
375 granted / 760 resolved
-12.7% vs TC avg
Strong +15% interview lift
Without
With
+15.1%
Interview Lift
resolved cases with interview
Typical timeline
3y 10m
Avg Prosecution
57 currently pending
Career history
817
Total Applications
across all art units

Statute-Specific Performance

§101
2.9%
-37.1% vs TC avg
§103
66.5%
+26.5% vs TC avg
§102
11.9%
-28.1% vs TC avg
§112
17.0%
-23.0% vs TC avg
Black line = Tech Center average estimate • Based on career data from 760 resolved cases

Office Action

§103
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 . Response to Arguments Applicant’s arguments with respect to claim(s) 1, 6, 8-11, 17-19 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. 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, 6, 8-11, 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over De Juan et al. (US2025/0131034) in view of Li et al. (US2022/0301117) and Yang (US2022/0148243). To claim 1, De Juan teach one or more computer storage media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations (Fig. 4), the operations comprising: accessing an image having one or more objects (paragraph 0032, user may provide a pre-existing image as user input); responsive to user input (paragraph 0032, using image editing tool, e.g., inpainting tool), applying a mask to the image to provide a masked image, the mask overlaying at least a portion of a first object from the one or more objects to define a region in which an inpainted object is to be added to the image to replace the first object (paragraphs 0007-0008, masking an area of target object for inpainting is known in the art; paragraphs 0078-0080; also well-known in the art, inpainting inherently involves masking, as it is fundamentally defined as the process of filling in, replacing, or editing specific, designated regions of an image while keeping the rest of the image unchanged); causing a generative model to generate an inpainted image replacing the first object with the inpainted object by inpainting the mask of the masked image with the inpainted object (paragraphs 0064, the user to update the image directly, paint over a portion of the image manually and/or with an inpainting model, relocate objects within the image, e.g., via automatically inpainting the object's original location and pasting and blending the object in the new location, and so forth); identifying one or more search results using the inpainted image; and providing the one or more search results for presentation (206-208 of Fig. 2; 314 of Fig. 3; paragraph 0063, provide the generated image as input to the image-based search algorithm; paragraphs 0065-0068); But, De Juan do not expressly disclose generating a query using one or more attributes of the inpainted object; searching an item data store using the query to identify one or more items having the one or more attributes; and providing, for presentation, one or more search results corresponding to the one or more items. However, De Juan does teach user may generate a query to search a database of images and receive the result for presentation to the user (paragraphs 0036-0068). Li teach image inpainting (abstract, paragraph 0033), wherein unwanted content is removed and replaced with replacement content (paragraphs 0031-0032, e.g., remove and replace furniture), wherein content can be searched and selected by user (paragraph 0048; Fig. 8A-B, paragraphs 0094-0096; Fig. 9, paragraphs 0097-0104). Yang further teach inpainting with reference object searched and selected by user from a plurality of candidate digital images maintained by service provider (604-608 of Fig. 6; paragraphs 0018, 0035-0038, 0045, e.g., visual similarity would be attribute of inpainted object for search). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate teachings of Li and Yang into the apparatus of De Juan, in order to further implementation of inpainting. To claim 11, De Juan, Li and Yang teach a computer-implemented method (as explained in response to claim 1 above). To claim 18, De Juan, Li and Yang teach a computer system (as explained in response to claim 1 above). To claim 6, De Juan, Li and Yang teach claim 1. De Juan, Li and Yang teach wherein searching the item data store further comprises: performing a visual search on an item data store using the inpainted image (obvious in image-based search algorithm of De Juan). To claim 8, De Juan, Li and Yang teach claim 1. De Juan, Li and Yang teach wherein generating the query using the one or more attributes of the inpainted object further comprises: generating an embedding using the one or more attributes of the inpainted object; and wherein the item data store is searched using the embedding (obvious in image-based search algorithm of De Juan; paragraphs 0049, 0068, may embed extra constraints and/or parameters into the query). To claim 9, De Juan, Li and Yang teach claim 8. De Juan, Li and Yang teach wherein the embedding comprises an multimodal embedding based on the one or more attributes of the inpainted object and the inpainted object in the inpainted image (obvious in image-based search algorithm of De Juan; despite lack of disclosing multimodal embedding, such feature is well-known query practice in the art, which would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate for improving search, hence Official Notice is taken). To claim 10, De Juan, Li and Yang teach claim 1. De Juan, Li and Yang teach wherein the operations further comprise: receiving a selection of a first search result from the one or more search results; generating a composite image by overlaying an object image corresponding to the first search result on one of the image, the masked image, or the inpainted image; and providing the composite image for presentation (obvious in 414 of Fig. 4 of De Juan, paragraph 0072, receive search result 414, a set of images of black long-sleeved shirts with tree designs, from the image-based search algorithm and may display and/or transmit search result 414 to the user; wherein the set of images would have been obviously interpreted as a composite image overlaying an object image corresponding to the first search result one of the image, hence Official Notice is also taken). To claim 17, De Juan, Li and Yang teach claim 11. De Juan, Li and Yang teach wherein the query is further generated using the inpainted object in the inpainted image (as taught by Yang). To claim 19, De Juan, Li and Yang teach claim 18. De Juan, Li and Yang teach wherein the operations further comprise determining one or more masked image attributes from analysis of the masked image; and wherein the one or more masked image attributes are provided as input to the generative model to generate the inpainted image (obvious in image-based search algorithm of De Juan, generation of inpainted image as explained in Stenger). Conclusion Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZHIYU LU whose telephone number is (571)272-2837. The examiner can normally be reached Weekdays: 8:30AM - 5:00PM. 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, Stephen R Koziol can be reached at (408) 918-7630. 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. ZHIYU . LU Primary Examiner Art Unit 2669 /ZHIYU LU/Primary Examiner, Art Unit 2665 April 7, 2026
Read full office action

Prosecution Timeline

Dec 04, 2023
Application Filed
Dec 20, 2025
Non-Final Rejection — §103
Feb 02, 2026
Examiner Interview Summary
Feb 02, 2026
Applicant Interview (Telephonic)
Mar 26, 2026
Response Filed
Apr 07, 2026
Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12597268
METHOD AND DEVICE FOR DETERMINING LANE OF TRAVELING VEHICLE BY USING ARTIFICIAL NEURAL NETWORK, AND NAVIGATION DEVICE INCLUDING SAME
2y 5m to grant Granted Apr 07, 2026
Patent 12596187
METHOD, APPARATUS, AND SYSTEM FOR WIRELESS SENSING MEASUREMENT AND REPORTING
2y 5m to grant Granted Apr 07, 2026
Patent 12592052
INFORMATION PROCESSING DEVICE, AND INFORMATION PROCESSING METHOD
2y 5m to grant Granted Mar 31, 2026
Patent 12581142
APPROACHES FOR COMPRESSING AND DISTRIBUTING IMAGE DATA
2y 5m to grant Granted Mar 17, 2026
Patent 12579698
METHOD AND APPARATUS OF ENCODING/DECODING POINT CLOUD GEOMETRY DATA CAPTURED BY A SPINNING SENSORS HEAD
2y 5m to grant Granted Mar 17, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

2-3
Expected OA Rounds
49%
Grant Probability
64%
With Interview (+15.1%)
3y 10m
Median Time to Grant
Moderate
PTA Risk
Based on 760 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in for Full Analysis

Enter your email to receive a magic link. No password needed.

Free tier: 3 strategy analyses per month