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 .
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 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 of this title, 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 1-2, 9-15 and 17-21 are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (US 2024/0064296) in view of Wang et al. (US 2022/0103864).
Regarding claim 1, Chen discloses a method for video processing (see fig. 17), comprising: applying a neural network (NN) filter (see Cov in fig. 17) to an unfiltered sample of a video unit (see input YUV in fig. 17) to generate a filtered sample (see RB in fig. 17), wherein the NN filter includes an NN filter model (see Cov in fig. 17) shared by both a luma component and a chroma component corresponding to the video unit (see YUV in fig. 17); and performing a conversion between a video media file and a bitstream based on the filtered sample (see YUV input and output in fig. 17).
Although Chen discloses granularity of the NN filter model (e.g. see ¶ [0074]), it is noted that Chen does not disclose wherein the granularity of the NN filter model specifies a size of the video unit to which the NN filter model is applied.
However, Wang discloses a neural network filtering wherein the granularity of the NN filter model specifies a size of the video unit to which the NN filter model is applied (e.g. see “granularity of selecting … model(s) … can be designed at different levels. The possible levels … a grid size N*N designed specifically for filter signaling” in ¶ [0086], [0088]).
Given the teachings as a whole, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate Wang teachings of granularity filter into Chen granularity filter coding information for the benefit of encoding and decoding with proper filtering with model to reduce image distortion.
Regarding claims 2 and 21, Chen further discloses wherein an output of the NN filter model depends on coding information (see fig. 6), and wherein the coding information is a syntax element included in the bitstream, or the coding information is derived information (see filter width and height derived from block size in fig. 6).
Regarding claim 9, Chen further discloses wherein the NN filter model is generated based on a scaling factor for the video unit (see QpMap in fig. 17), and the output of the NN filter model depends on the scaling factor (see YUV output in fig. 17).
Regarding claim 10, Chen further discloses wherein the scaling factor indicates a factor scaling a difference between a reconstruction of the video unit and the output of the NN filter model (e.g. see ¶ [0114]).
Regarding claim 11, Chen further discloses wherein the coding information is represented by an MxN array (see 64x64x3 in fig. 6).
Regarding claim 12, Chen further discloses wherein M and N represent a width and a height of the video unit (see 64x64x3 in fig. 6) or
Regarding claim 13, Chen further discloses wherein the coding information is represented by numbers (see 64x64x3 in fig. 6).
Regarding claim 14, the references further discloses wherein the granularity of the NN filter model is included in the bitstream or derived (e.g. see Wang ¶ [0086], [0088]).
Regarding claim 15, the references further discloses wherein in response to the granularity of the NN filter model being included in the bitstream, indication of the granularity is signalled in a sequence header, a picture header, a slice header, a sequence parameter set (SPS), a picture parameter set (PPS), or an adaptation parameter set (APS) (e.g. see Wang ¶ [0086], [0088]).
Regarding claim 17, Chen further discloses wherein the conversion comprises generating the bitstream according to the video media file (see 114 in fig. 1).
Regarding claim 18, Chen further discloses wherein the conversion comprises parsing the bitstream to obtain the video media file (see 201, 202 and 222 in fig. 2).
Regarding claim 19, the claim(s) recite an apparatus (see figs. 1-2) analogous limitations to claim 1, and is/are therefore rejected on the same premise.
Regarding claim 20, the claim(s) recite analogous limitations to claim 1, and is/are therefore rejected on the same premise.
Response to Arguments
Applicant's arguments filed 6/17/26 have been fully considered but they are not persuasive. Applicant argued that Wang “fails to disclose the granularity of the NN filter model specifies a size of the video unit to which the NN filter model is applied” because “Wang merely mentions that the granularity of selecting and signaling the model(s) can be designed at different levels”. The Examiner respectfully disagrees. Wang stated that granularity of filter model goes hand in hand with granularity size (e.g. see “granularity of selecting … model(s) … can be designed at different levels. The possible levels … a grid size N*N designed specifically for filter signaling” in ¶ [0086], [0088]”, wherein Wang ¶ [0130] clearly states that this grid has a size of rows and column of a partitioned picture). Therefore, the Examiner maintains all limitations are met.
Citation of Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
1. Piao et al. (US 2023/0044603), discloses AI based image filtering.
2. Dai (US 2024/0107073), discloses AI based image filtering.
3. Andersson et al. (US 2025/0071283), discloses neural network based image filtering.
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 RICHARD T TORRENTE whose telephone number is (571)270-3702. The examiner can normally be reached M-F: 6:45-3:15 pm.
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, Jay Patel can be reached at (571) 272-2988. 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.
/RICHARD T TORRENTE/Primary Examiner, Art Unit 2485
Prosecution Insights