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 Amendment
Applicant’s amendment was received on 4/24/26 and has been entered and made of record. Currently, claims 1-12 are pending.
Drawings
The drawings were received on 4/24/26. These drawings are accepted.
Applicant’s amendment to the specification and to Fig. 1 has overcome the objection set forth in the previous Office Action and has therefore been withdrawn.
Claim Rejections - 35 USC § 101
Applicant’s amendment to claim 121 has overcome the rejection set forth in the previous Office Action and has therefore been withdrawn.
Response to Arguments
Applicant’s arguments, see pages 10-11 of the remarks, filed 4/24/26, with respect to the rejection(s) of claim(s) 1, 11, and 12 under 35 U.S.C 102(a)(1) have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of newly found prior art necessitated by the current amendment.
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.
Claims 1-3 and 8-12 are rejected under 35 U.S.C. 103(a) as being unpatentable over Zheng et al. (US 12,430,727) in view of Wang et al. (“Semantic Image Synthesis via Diffusion Models”), cited in the IDS dated 7/25/25, and Xie et al. (US 2024/0169622).
Regarding claims 1, 11, and 12, Zheng discloses a computer program stored in a computer-readable medium, an apparatus for generating semantic images using condition image diffusion, the apparatus comprising: one or more processors (processor unit 205); a network interface (Fig. 1, image processing apparatus 110 can communicate with other devices via cloud 115); a memory (memory unit 210) for loading a computer program executed by the processors; and a storage for storing large-capacity network data (database 120) and the computer program, and a method of generating semantic images using condition image diffusion, by an apparatus including a processor and a memory, the method comprising the steps of:
(a) training an image generation model by inputting N-th learning data (herein, N is a random positive integer) (see Fig. 10 and col 10 lines 46-60, and col 18 lines 15-41, a diffusion model receives training images);
(b) inputting input data for generating semantic images into the trained image generation model (see Fig. 10 and col 10 lines 46-60, and col 18 lines 15-41, a diffusion model adds noise to images and generates a set of intermediate semantic images); and
(c) outputting one or more semantic images generated by the image generation model according to the input data, and wherein, a different number is assigned to pixel areas occupied by the classes for each classified category (see Fig. 10 and col 7 line 62-col 8 line 24, col 8 lines 53-64, col 18 lines 42-57, and col 19 lines 37-45, a pixel diffusion model can be trained with noisy images using a perceptual loss, reverse diffusion is performed to acquire predicted image and image features that are then compared to actual image and image features to output a final semantic image).
Zheng does not disclose expressly wherein the input data is a condition image frame (Semantic Layout) corresponding to an input condition and wherein, through the condition image frame, classes, which are one or more objects included in a semantic image to be generated, are classified into each category by the object.
Wang discloses wherein the input data is a condition image frame (Semantic Layout) corresponding to an input condition (see page 2, left hand column, para 1, and sections 2.2, 3.2, 3.3, and 4.4, the semantic diffusion model utilizes semantic layout in the processing of the image data).
Xie discloses wherein, through the condition image frame, classes, which are one or more objects included in a semantic image to be generated, are classified into each category by the object (see paras 78, 160-161, and 167, classification of objects found in image data is performed)
Before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to combine the semantic layout processing, as described by Wang, and the object classification, as described by Xie, with the system of Zheng.
The suggestion/motivation for doing so would have been to improve image generation quality.
Therefore, it would have been obvious to combine Wang and Xie with Zheng to obtain the invention as specified in claims 1, 11 , and 12.
Regarding claim 2, Zheng further discloses wherein step (a) includes steps of: (a-1) generating N'-th learning data by adding noise to the N-th learning data through selection of any one among first to fourth noise addition methods (see Fig. 10 and col 10 lines 46-60, and col 18 lines 15-41, a diffusion model receives training images);
(a-2) predicting noise applied to the N'-th learning data by inputting the generated N'-th learning data into the image generation model (see col 18 lines 24-57, a diffusion model adds noise to images and generates a set of intermediate semantic images); and
(a-3) comparing the noise added at step (a-1) with the noise predicted at step (a-2), setting a difference thereof as a loss function, and learning by applying gradient descent (see col 18 lines 24-57, a pixel diffusion model can be trained with noisy images using a perceptual loss, reverse diffusion is performed to acquire predicted image and image features that are then compared to actual image and image features to output a final semantic image, gradient descent is utilized) .
Regarding claim 3, Zheng further discloses wherein step (a) further includes steps of: (a-4) determining whether the set loss function converges to a minimum value; (a-5) returning to step (a-1) when a result of the determination at step (a-4) is NO; and (a-6) terminating learning of the image generation model when the result of the determination at step (a-4) is YES (see Fig. 9 and col 15 line 36-col 16 line 62, a pixel diffusion model can be trained with noisy images using a perceptual loss, an iterative process is performed).
Regarding claim 8, Zheng further discloses wherein the N-th learning data is an N-th real image, and step (a-2) includes steps of: (a-2-1) inputting the generated N′-th learning data into the image generation model; (a-2-2) inputting N-th input condition data, which is obtained by adding noise to an N-th condition image frame corresponding to the N-th real image through any one among the first to fourth noise addition methods, into the image generation model; and (a-2-3) predicting noise applied to the N′-th learning data by reflecting the input N-th input condition data (see Fig. 10 and col 10 lines 46-60, and col 18 lines 15-57, a diffusion model receives training images, the diffusion model adds noise to images and generates a set of intermediate semantic images, a pixel diffusion model can be trained with noisy images using a perceptual loss, reverse diffusion is performed to acquire predicted image and image features that are then compared to actual image and image features to output a final semantic image, gradient descent is utilized).
Regarding claim 9, Zheng further discloses wherein step (b) includes steps of: (b-1) randomly generating noise data of a size the same as that of the semantic image desired to be generated, and inputting the noise data into the image generation model as input data; and (b-2) generating input condition data by adding noise to a condition image frame for generating a semantic image through any one of the first to fourth noise addition methods, and inputting the input condition data into the image generation model (see col 3 lines 34-45, col 4 lines 4-11, col 10 lines 46-60, the diffusion model is trained using an adaptively-blurred perceptual loss by applying a Gaussian kernel of different sizes to the predicted images and ground-truth images).
Regarding claim 10, Zheng further discloses wherein the image generation model includes an encoder unit and a decoder unit, and the image generation model further includes a condition image frame utilization unit including one or more convolution layers that acquire feature values from the condition image frame and calculate a scale value and a bias value by passing the feature values, wherein the calculated scale value and bias value are acquired from the input data, and input into the batch normalized feature values to be calculated (see Figs. 3 and 5 and col 10 lines 46-60, col 11 line 66-col 12 line 8, and col 12 lines 43-48, a forward diffusion process 315 acts as an encoder, a reverse diffusion process 325 acts as a decoder, convolution layers are utilized).
Allowable Subject Matter
Claims 4-7 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
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 MARK R MILIA whose telephone number is (571) 272-7408. The examiner can normally be reached Monday-Friday, 8am-5pm.
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, Akwasi Sarpong can be reached at 571-270-3438. The fax 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.
/MARK R MILIA/Primary Examiner, Art Unit 2681
Prosecution Insights