CTFR 18/455,298 CTFR 90179 DETAILED ACTION This Office Action is a response to a Pre-Appeal Brief filed on 09/04/2025, in which claims 1-20 are pending and ready for examination. Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia 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 claims 1-20 have been considered but are not persuasive. In regards to claims 1 applicant argues that the combination of Andreopoulos and Qiu fail to disclose the limitation of “generating encoded frame data by encoding a current frame from an input video, wherein encoding the current frame includes using a neural-network-based video quality model”. However, Examiner respectfully disagrees. Both references Andreopoulos and Qiu teach the process of generating encoded frame data by encoding a current frame from an input video. More specifically, as shown in Fig. 8 and explained in paragraph 63 of Andreopoulos, input image data representing at least one image is received and the input image data is encoded at an encoding stage comprising a network of inter- connected weights to generate encoded image data. Please note that the encoding stage comprises the network of inter-connected weight, and the network of inter-connected weights of the encoding stage are obtained based on distortion difference score and rate difference score (see Fig. 8 step 870). As disclosed in paragraph 67, a neural network model is used to measure distortion difference and rate difference scores. So, a neural-network model is used to generate the encoded bitstream outputted by the standard encoder. Although, Andreopoulos talks about generating distortion maps and couples the distortions with a neural network rate prediction model, but Andreopoulos does not explicitly disclose a “neural-network-based video quality model”. On the other hand, Qiu clearly discloses an encoder that generates encoded video frame based on a mapping, and the mapping is implemented using a neural network model that uses quality metrics to optimize settings which impacts perceptual quality. Thus, the combination of Andreopoulos and Qiu fully disclose all the limitations of claim 1, and the claim remains rejected. Claims 1-20 remain rejected since the system disclosed by the applicant is taught by the prior arts. Claim Rejections - 35 USC § 103 07-20-aia AIA 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. 07-21-aia AIA Claim s 1-4, 7-12, and 14-20 are rejected under 35 U.S.C. 103 as being unpatentable over Andreopoulos (US 2021/0211684 A1) in view of Qiu (US 2020/0137389 A1) . Regarding claim 1 , Andreopoulos discloses: A method comprising: generating encoded frame data by encoding a current frame from an input video (see paragraph 67, step (i)) , using a neural-network-based model (see paragraph 67) ; and outputting the encoded frame data (see Fig. 4) . Although Andreopoulos discloses using neural network model in the process of generating the encoded date, but does not explicitly disclose: wherein encoding the current frame includes using a neural-network-based video quality model. However, Qiu from the same or similar endeavor discloses: wherein encoding the current frame includes using a neural-network-based video quality model (see Qiu, paragraph 32 and Fig. 7, encoder encodes the received video frame based on a mapping, and the mapping is implemented using neural network model that uses quality metrics) . It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to encode “the current frame using a neural-network-based video quality model” as taught by Qiu in the video coding method and apparatus taught by Andreopoulos to optimize settings which impacts perceptual quality (see Qiu, paragraph 32) . Regarding claim 2 , the combination of Andreopoulos and Qiu discloses: The method of claim 1, wherein encoding the current frame using the neural-network-based video quality model (see Andreopoulos, paragraph 67) includes: obtaining a neural-network-based video quality model generated gradient map generated for the current frame by the neural-network-based video quality model (see Andreopoulos, paragraph 67) ; obtaining a current block from the current frame (see Andreopoulos, Fig. 1) ; identifying optimal encoding parameters for encoding the current block from a plurality of available encoding parameters, wherein the optimal encoding parameters minimizes a rate-distortion optimization cost function relative to the plurality of available encoding parameters (see Andreopoulos, paragraph 53) , wherein minimizing the rate-distortion optimization cost function includes using a gradient value for the current block obtained from the neural-network-based video quality model generated gradient map (see Andreopoulos, paragraphs, 17, 51, and 67) ; obtaining encoded block data by encoding the current block using the optimal encoding parameters (see Andreopoulos, Fig. 4) ; and including the encoded block data in the encoded frame data (see Andreopoulos, Fig. 4) . Regarding claim 3 , the combination of Andreopoulos and Qiu discloses: The method of claim 2, wherein obtaining the neural-network-based video quality model generated gradient map (see Andreopoulos, paragraph 67) includes: using the current frame as input to the neural-network-based video quality model (see Andreopoulos, Fig. 4) ; and receiving the neural-network-based video quality model generated gradient map from the neural-network-based video quality model (see Andreopoulos, paragraph 67 and Fig. 4) . Regarding claim 4 , the combination of Andreopoulos and Qiu discloses: The method of claim 3, wherein obtaining the neural-network-based video quality model generated gradient map (see Andreopoulos, paragraph 67) includes: omitting using a frame other than the current frame as input to the neural-network-based video quality model (see Andreopoulos, Fig. 1 and paragraph 57, local spatial region of each frame) . Regarding claim 7 , the combination of Andreopoulos and Qiu discloses: The method of claim 2, further comprising: obtaining a reconstructed frame by decoding the encoded frame data (see Andreopoulos, Fig. 1, external decoder outputs a reconstructed image) ; obtaining a second neural-network-based video quality model generated gradient map generated for the reconstructed frame from the neural-network-based video quality model (see Andreopoulos, paragraph 67) ; obtaining a restoration filtered reconstructed frame by restoration filtering the reconstructed frame using the second neural-network-based video quality model generated gradient map (see Andreopoulos, paragraphs, 52, 67, and 75) ; and storing the restoration filtered reconstructed frame for use as a reference frame for encoding another frame (see Andreopoulos, Fig. 1) . Regarding claim 8 , the combination of Andreopoulos and Qiu discloses: The method of claim 1, wherein encoding the current frame includes: obtaining a reconstructed frame by decoding the encoded frame data (see Andreopoulos, Fig. 1, external decoder outputs a reconstructed image) ; obtaining a neural-network-based video quality model generated gradient map generated for the reconstructed frame from the neural-network-based video quality model (see Andreopoulos, paragraph 67) ; obtaining a restoration filtered reconstructed frame by restoration filtering the reconstructed frame using the neural-network-based video quality model generated gradient map (see Andreopoulos, paragraphs, 52, 67, and 75) ; and storing the restoration filtered reconstructed frame for use as a reference frame for encoding another frame (see Andreopoulos, Fig. 1) . Regarding claims 9-12 and 14-16 , claims 9-12 and 14-16 are drawn to an apparatus having limitations similar to the method claimed in claims 1-4 and 7-8 treated in the above rejections. Therefore, apparatus claims 9-12 and 14-16 correspond to method claims 1-4 and 7-8 and are rejected for the same reasons of anticipation as used above. Regarding claim 17 , Andreopoulos discloses: A method comprising: obtaining an encoded bitstream (see Fig. 1, external decoder receives the bitstream) ; obtaining encoded frame data from the encoded bitstream (see Fig. 1) ; obtaining a reconstructed frame by decoding the encoded frame data (see Fig. 1, external decoder outputs a reconstructed image) ; obtaining restoration filtered reconstructed frame data (see Fig. 1) by: obtaining, from a neural-network-based video quality model, a neural-network-based video quality model generated gradient map generated for the reconstructed frame (see paragraph 67, also see paragraph 17, the decoding stage mirrors that of the encoding stage) ; and generating restoration filtered reconstructed frame data by restoration filtering the reconstructed frame using the neural-network-based video quality model generated gradient map (see paragraph 52, 67, and 75) ; and storing the restoration filtered reconstructed frame for use as a reference frame for encoding another frame (see Fig. 1) . Although Andreopoulos discloses using neural network model in the process of generating the encoded date, and as mentioned in paragraph 17, the decoding stage mirrors that of the encoding stage, but does not explicitly disclose: wherein encoding the current frame includes using a neural-network-based video quality model. However, Qiu from the same or similar endeavor discloses: wherein encoding the current frame includes using a neural-network-based video quality model (see Qiu, paragraph 32 and Fig. 7, encoder encodes the received video frame based on a mapping, and the mapping in implemented using neural network model that uses quality metrics) . It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to encode “the current frame includes using a neural-network-based video quality model” as taught by Qiu in the video coding method and apparatus taught by Andreopoulos to optimize settings which impacts perceptual quality (see Qiu, paragraph 32) . Regarding claim 18 , the combination of Andreopoulos and Qiu discloses: The method of claim 17, wherein: in response to determining that in-loop restoration filtering using the neural-network-based video quality model generated gradient map is enabled, storing the restoration filtered reconstructed frame includes including the restoration filtered reconstructed frame in an output video stream (see Andreopoulos, paragraph 29 and Fig. 1) . Regarding claim 19 , the combination of Andreopoulos and Qiu discloses: The method of claim 17, wherein: in response to determining that in-loop restoration filtering using the neural-network- based video quality model generated gradient map is unavailable, obtaining the reconstructed frame includes including the reconstructed frame in an output video stream (see Andreopoulos, paragraph 29 and Fig. 1) . Regarding claim 20 , the combination of Andreopoulos and Qiu discloses: The method of claim 17, wherein restoration filtering the reconstructed frame using the neural-network-based video quality model generated gradient map (see Andreopoulos, paragraph 52, 67, and 75) includes: obtaining a current reconstructed block from the reconstructed frame (see Andreopoulos, paragraph 28) ; obtaining a restoration filtered reconstructed block as a sum of (see Andreopoulos, Fig. 2(a)) : the current reconstructed block (see Andreopoulos, Fig. 2(a)) ; and a result of: dividing: a product of multiplying a learning rate by a gradient value from the gradient map for the current reconstructed block (see Andreopoulos, Fig. 2(a) and paragraph 51-52) ; by a Euclidean norm of the gradient value (see Andreopoulos, paragraph 28) . Allowable Subject Matter 12-151-08 AIA 07-43 12-51-08 Claim s 5-6 and 13-14 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 07-39 AIA THIS ACTION IS MADE FINAL. 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 MARYAM A NASRI whose telephone number is (571)270-7158. The examiner can normally be reached 10:00-8:00 M-T. 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, Joseph Ustaris can be reached on 5712727383. 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. /MARYAM A NASRI/Primary Examiner, Art Unit 2483 Application/Control Number: 18/455,298 Page 2 Art Unit: 2483 Application/Control Number: 18/455,298 Page 3 Art Unit: 2483 Application/Control Number: 18/455,298 Page 6 Art Unit: 2483 Application/Control Number: 18/455,298 Page 7 Art Unit: 2483 Application/Control Number: 18/455,298 Page 8 Art Unit: 2483 Application/Control Number: 18/455,298 Page 9 Art Unit: 2483 Application/Control Number: 18/455,298 Page 10 Art Unit: 2483 Application/Control Number: 18/455,298 Page 11 Art Unit: 2483
Prosecution Insights