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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Claim Rejections - 35 USC § 102
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.
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1 and 15 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Bordes et al (2023/0188713).
In regard to claim 1 Bordes discloses a method performed by an electronic device, for artificial intelligence (AI) based encoding of media (Bordes Fig. 10), the method comprising:
compressing an input image frame associated with an input video (Bordes Fig. 10 and par. 89 note video encoder 1010 compressing input video);
generating, by an AI-based in-loop filter, a reconstructed image frame corresponding to the input image frame (Bordes Fig. 10 and pars. 90-92 note reconstructed video Ŝ output to the decoded picture buffer DPB);
determining an offset value based on the input image frame and the reconstructed image frame (Bordes Fig. 10 and pars 90-91 note ComputeavOffset which determines an offset value); and
encoding the reconstructed image frame based on the offset value (Bordes Fig. 10 note frame reconstructed using the offset value is used by the encoder in the decoded picture buffer DPB also note the offset is included in the encoded bitstream).
Claim 15 describes a system comprising a memory and a processor method substantially corresponding to the method described by claim 1. refer to the statements made in regard to claims 1 and 8 above for the rejection of claim 15 which will not be repeated here for brevity. In particular regard to claim 15 Bordes further discloses a processor and a memory (Bordes Fig. 1 note processor 110 and memory 120).
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) 2, 6-14, 16 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Bordes in view of Chen et al (2022/0337824).
In regard to claims 2 and 16 refer to the statements made in the rejection of claims 1 and 15 above. It is noted that Bordes does not disclose generating an offset value based on data distributions.
However, Chen discloses an AI-based in-loop filter that determines offset values by:
generating a model output data distribution of the reconstructed image frame (Chen pars 96-115 note samples after applying a neural network loop filter (NNLF) as output data distribution);
generating a ground-truth data distribution of the input image frame (Chen pars 96-115 note samples before applying a NNLF as the ground-truth data distribution) ; and
determining the offset value based on the model output data distribution and the ground-truth data distribution (Chen pars 96-115 particularly note pars 99-103 for determining offsets for various texture edge categories based on aggregate distortions between the pre NNLF samples a and the post NNLF samples).
It is therefore considered obvious that one of ordinary skill in the art before the effective filing date of the invention would recognize the advantage of incorporating and offset determining method as taught by Chen in the invention of Bordes in order to gain the advantage of adapting the supplied offsets to the content of the image as suggested by Chen (Chen par. 103).
In regard to claim 6 refer to the statements made in the rejection of claim 2 above. Bordes and Chen further discloses that the determining of the offset value based on the model output data distribution and the ground-truth data distribution comprises:
determining, in a form of a per-fragment offset, a pixel mapping using the model output data distribution, the ground-truth data distribution, and a mapping extent (Chen prs 96-115 note an offset is determined for each class, or fragment, based on the difference between the pre NNLF, or ground truth, samples and the post NNLF, or output, samples, further note Bordes pars 86-97 which discloses a weight mask, or mapping extent, that controls how block level offsets are applied to individual samples within the block).
In regard to claim 7 refer to the statement made in the rejection of claim 6 above. Bordes further discloses that:
determining the mapping extent based on a number of fragments and a codec rate distortion cost, the mapping extent indicating whether to apply an offset scaling to a fragment on a basis of an RD cost (Bordes pars 89-92 note NNLF determining an offset and a weight mask, or mapping extent, using a minimization method, further note pars 148-149 the NNLF minimization minimizes a rate distortion measure).
In regard to claim 8 refer to the statements made in the rejection of claim 1 above. the encoding of the reconstructed image frame comprises:
performing a scaling operation on the reconstructed image frame based on the offset value to generate a scaled image frame, the scaling operation comprising at least one of an addition operation, a multiplication operation, a division operation, or an exponential operation (Bordes pars 89-92 note the weight matrix as a scaling parameter that is applied to scale the offset value to generate a filtered image frame) ; and
encoding the scaled image frame (Bordes Fig. 10 note encoding the image frame) .
In regard to claim 9 refer to the statements made in the rejection of claim 1 above. Bordes further discloses that generating of the reconstructed image frame comprises:
generating, by using one or more neural network (NN) models of the AI-based in-loop filter, the reconstructed image frame (Bordes Fig. 10 and pars. 90-92 note reconstructed video Ŝ generated by a neural network based loop filter or NNLF).
In regard to claim 10 refer to the statements made in the rejection of claim 1 above. Bordes further discloses sending, to a decoder, bitstream information associated with the reconstructed image frame, the bitstream information comprising the offset value (Bordes Figs. 10 and 13 and pars 92 and 98 note bitstream output from the encoder at 1050, further note the bitstream output from the encoder is input to the decoder as shown in Fig. 13).
In regard to claims 11 and 20 refer to the statements made in the rejection of claims 1-2 and 15-16 above. Chen further discloses determining of the offset value at a per-fragment granularity (Chen pars 96-115 particularly note pars 99-103 for determining offsets for each of various texture edge categories, or ‘fragments’).
Claims 12-14 describe a method substantially corresponding to the method described by claims 1 and 8 above. refer to the statements made in regard to claims 1 and 8 above for the rejection of claim 12 which will not be repeated here for brevity. In particular regard to claim 14 Chen discloses that the scaling operation comprises a multiplication and addition operation (Chen Fig. 10 note multiplication and addition used in applying the weight mask to the image samples).
Allowable Subject Matter
Claims 3-5 and 17-19 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.
The following is a statement of reasons for the indication of allowable subject matter:
Claims 3 and 17, in addition to the limitations of claims 2 and 16 from which the depend, further require identifying a number of fragments based on user input fragmenting the reconstructed image based on the number and analysis of frame content, performing pixel binning and generating data points based representing optimal fragmentation based on the binning.
The closest arts are Bordes and Chen. Bordes discloses applying an AI filtering operation to determine offset value and a scaling pixel mapping operation used in encoding video. Chen discloses determining a number of texture edge classes and using a neural network filtering operation to determine optimum offset values for each texture edge class. Fu et al (2012/01771403) further discloses that a number of texture edge classes may be set based on user input (Fu par. 33 note the number of SAO categories may be based on user input). However, none of the prior arts alone or in combination disclose the particular combination of features required by dependent claims 3 and 17.
Claims 4-5 and 18-19 depend from claims 3 and 17 respectively and are objected to for the same reasons.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20240333923 A1 KIM; Hyun Gyu et al.
US 20240155119 A1 STRÖM; Jacob et al.
US 20220295116 A1 MA; Shoujiang et al.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JEREMIAH CHARLES HALLENBECK-HUBER whose telephone number is (571)272-5248. The examiner can normally be reached Monday to Friday from 9 A.M. to 5 P.M.
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, William Vaughn can be reached at (571)272-3922. 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.
/JEREMIAH C HALLENBECK-HUBER/Primary Examiner, Art Unit 2481
Prosecution Insights