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 .
A telephone call was made on 03/16/2026, to Applicant representative Shelton Austin to request an oral election to the restriction requirements as being explained below. Mr. Austin elected without traverse of Group III (claims 20-28), is acknowledged.
Election/Restriction
This application contains claims directed to the following patentably distinct species:
Species I is an embodiment, Figure 14, directed to Claims 1-9.
Species II is an embodiment, Figure 15, directed to Claims 10-19.
Species III is an embodiment, Figure 16, directed to Claims 20-28.
The Species I, Species II and Species III are independent or distinct because: Species I pertains to operations that processes tokens using diffusion model, Species II deals with operations that generates and merges tokens based on segmentation mask as shown in Figure 15, and Species III deals with generation of modified image data based on modified portions of image data, as shown in Figure 16. In addition, they are not obvious variants of each other based on the current record.
Applicant is required under 35 U.S.C. 121 to elect a single disclosed species, or a single grouping of patentably indistinct species, for prosecution on the merits to which the claims shall be restricted if no generic claim is finally held to be allowable. Currently, no generic claims are present. There is a search and/or examination burden for the patentably distinct species as set forth above Species I-III.
Applicant is advised that the reply to this requirement to be complete must include (i) an election of a species to be examined even though the requirement may be traversed (37 CFR 1.143) and (ii) identification of the claims encompassing the elected species or grouping of patentably indistinct species, including any claims subsequently added. An argument that a claim is allowable or that all claims are generic is considered nonresponsive unless accompanied by an election.
The election may be made with or without traverse. To preserve a right to petition, the election must be made with traverse. If the reply does not distinctly and specifically point out supposed errors in the election of species requirement, the election shall be treated as an election without traverse. Traversal must be presented at the time of election in order to be considered timely. Failure to timely traverse the requirement will result in the loss of right to petition under 37 CFR 1.144. If claims are added after the election, Applicant must indicate which of these claims are readable on the elected species or grouping of patentably indistinct species.
Should Applicant traverse on the ground that the species, or groupings of patentably indistinct species from which election is required, are not patentably distinct, Applicant should submit evidence or identify such evidence now of record showing them to be obvious variants or clearly admit on the record that this is the case. In either instance, if the Examiner finds one of the species unpatentable over the prior art, the evidence or admission may be used in a rejection under 35 U.S.C. 103 or pre-AIA 35 U.S.C. 103(a) of the other species.
Upon the allowance of a generic claim, Applicant will be entitled to consideration of claims to additional species which depend from or otherwise require all the limitations of an allowable generic claim as provided by 37 CFR 1.141.
Claim Objections
Claim 21, objected to because of the following informalities: In claim 21, line 3, recites “resulting in modified image data”, however should recite “resulting in the modified image data”. Appropriate correction is required.
Claim 22, objected to because of the following informalities: In claim 22, lines 6-7, recites “generate modified image data”, however should recite “generate the modified image data”. Appropriate correction is required.
Claim 24, objected to because of the following informalities: Currently claim 24, depends on claim 20, however should depend on claim 21, since first time “combine” step is being introduced in claim 21. Appropriate correction is required.
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) 20-21, 23-24, and 27-28, is/are rejected under 35 U.S.C. 103 as being unpatentable over Guillaume (NPL Document “DiffEdit: Diffusion-based semantic image editing with mask guidance” provided by Applicant in the IDS filed on 10/29/2025) and further in view of Jahromi (US PGPUB 2022/0139180 A1).
As per claim 20, Guillaume discloses an apparatus for modifying image data (Guillaume, page 1, Abstract, discloses task of semantic image editing, and page 6, paragraph 3, discloses GP100 GPU), the apparatus comprising:
one or more processors (Guillaume, page 6, paragraph 3, discloses GP100 GPU) configured to:
identify a first portion of image data and a second portion of the image data based on a segmentation mask (Guillaume, page 4, Fig. 2, shows “Mask M”, where the first image portion is the inside of the mask and second image portion is the outside of the mask);
process the first portion of the image data using a diffusion model to generate a modified first portion of the image data (Guillaume, page 4, Fig. 2, items “yr”, “yt” and “DDIM step”, where DDIM is the diffusion model, process yr, which includes the first portion and yt, which includes a modified first portion of the image data); and
generate modified image data based on the modified first portion of the image data and the second portion of the image data (Guillaume, page 4, Fig. 2, “yt=M.yt+(1-M).xt”, where yt is the modified image data, M.yt is the modified first portion of the data and (1-M).xt is a noised version of the second portion of the data).
Guillaume does not explicitly disclose one or more memories configured to store the image data; and
one or more processors coupled to the one or more memories,
Marchesotti discloses one or more memories configured to store the image data (Jahromi, Fig. 1:106); and
one or more processors (Jahromi, Fig. 1:104) coupled to the one or more memories (Jahromi, Fig. 1:106:104),
it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guillaume teachings by implementing a memory to the system, as taught by Jahromi.
The motivation would be to provide a system with improved event detection (paragraph 41), as taught by Jahromi.
As per claim 21, Guillaume in view of Jahromi further discloses the apparatus of claim 20, wherein, to generate the modified image data, the one or more processors is configured to combine the modified first portion of the image data and the second portion of the image data resulting in modified image data (Guillaume, page 4, Fig. 2, “yt=M.yt+(1-M).xt”, the modified image data is combination of the modified first portion and second portion of the image data).
As per claim 23, Guillaume in view of Jahromi further discloses the apparatus of claim 20, wherein the segmentation mask is based on at least one of: a foreground-background segmentation; a saliency segmentation; or a cross-attention map from latent representations (Guillaume, page 4, Fig. 2, “Step 1:compute mask” perform a foreground-background segmentation of the input image where the foreground is defined by the input text).
As per claim 24, Guillaume in view of Jahromi further discloses the apparatus of claim 20, wherein, to combine the modified first portion of the image data and the second portion of the image data, the one or more processors are configured to blend pixels from the modified first portion of the image data and the second portion of the image data (Guillaume, page 4, Fig. 2, “yt=M.yt+(1-M).xt”,, is a special form of alpha blending where alpha is worth 1 or 0 depending on the location. Furthermore, repeated DDIM step operation also operate a blending of the first portion of the image dadta with the second portion of the image data).
As per claim 27, Guillaume in view of Jahromi further discloses the apparatus of claim 20, further comprising at least one camera configured to capture the image data (Jahromi, Fig. 1:120, camera).
As per claim 28, Guillaume in view of Jahromi further discloses the apparatus of claim 20, further comprising a display configured to display the modified image data (Guillaume, page 1, Fig. 1, modified image data displayed as shown in Fig. 1).
Claim(s) 22, is/are rejected under 35 U.S.C. 103 as being unpatentable over Guillaume (NPL Document “DiffEdit: Diffusion-based semantic image editing with mask guidance” provided by Applicant in the IDS filed on 10/29/2025) and further in view of Jahromi (US PGPUB 2022/0139180 A1) and further in view of Zhang (NPL Document “Inversion-Based Style Transfer with Diffusion Models”, provided by Applicant in the IDS filed on 10/29/2025).
As per claim 22, Guillaume in view of Jahromi further discloses the apparatus of claim 20, wherein: the first portion of the image data is processed through a first number of diffusion steps of the diffusion model to generate the modified first portion of the image data (Guillaume, page 4, Fig. 2, items “yr”, “yt” and “DDIM step”, where DDIM is the diffusion model, process yr, which includes the first portion and yt, which includes a modified first portion of the image data); and
Guillaume in view of Jahromi does not explicitly disclose to generate the modified image data, the one or more processors is configured to process the modified first portion of the image data and the second portion of the image data using a second number of diffusion steps of the diffusion model to generate modified image data.
Zhang discloses to generate the modified image data, the one or more processors is configured to process the modified first portion of the image data and the second portion of the image data using a second number of diffusion steps of the diffusion model to generate modified image data (Zhang, page 10148, Fig. 3, please see “noise version II”, “conditioned synthesis process”, and “result” where the noise version II is an image with a foreground and background i.e., a first portion and second portion of image data, where the conditioned synthesis process is the diffusion model and the result is the modified image data).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guillaume in view of Jahromi teachings by generating a processed image, as taught by Zhang.
The motivation would be to provide an improved system to control the content of modified image (page 10147, second paragraph), as taught by Zhang.
Claim(s) 25-26, is/are rejected under 35 U.S.C. 103 as being unpatentable over Guillaume (NPL Document “DiffEdit: Diffusion-based semantic image editing with mask guidance” provided by Applicant in the IDS filed on 10/29/2025) and further in view of Jahromi (US PGPUB 2022/0139180 A1) and further in view of Tack (US PGPUB 2025/0005723 A1).
As per claim 25, Guillaume in view of Jahromi further discloses the apparatus of claim 20, wherein the first portion of the image data is cropped from the image data.
Guillaume in view of Jahromi does not explicitly disclose first portion of the image data is cropped from the image data.
Tack discloses first portion of the image data is cropped from the image data (Tack, paragraphs 65-66 and 108, discloses cropping the original image).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guillaume in view of Jahromi teachings by implementing image editing application to the system, as taught by Tack.
The motivation would be to improve the quality and resolution of the generated visual element (paragraph 108), as taught by Tack.
As per claim 26, Guillaume in view of Jahromi further discloses the apparatus of claim 20, wherein the Guillaume in view of Jahromi does not explicitly disclose first portion of the image data comprises a rectangular portion cropped from the image data.
Tack discloses first portion of the image data comprises a rectangular portion cropped from the image data (Tack, paragraph 108, discloses cropped area may be rectangular).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guillaume in view of Jahromi teachings by implementing image editing application to the system, as taught by Tack.
The motivation would be to improve the quality and resolution of the generated visual element (paragraph 108), as taught by Tack.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SYED Z HAIDER whose telephone number is (571)270-5169. The examiner can normally be reached MONDAY-FRIDAY 9-5:30 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, SAM K Ahn can be reached at 571-272-3044. 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.
/SYED HAIDER/Primary Examiner, Art Unit 2633