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 . 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. There are a total of 15 claims and claims 1,4-7,9-15 and 18-20 are pending.
Response to Amendment
Applicant's argument, filed on March 16, 2026 has been entered and carefully considered. Claims 1, 15 and 20 are amended and claims 2,3,8, 16 and 17 are canceled. Claims 1,4-7,9-15 and 18-20 are pending.
Response to Arguments
2. Applicant’s arguments filed on 03/16/2026 with respect to the rejection(s) of claim(s) 1, 15 and 20 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 Therefore, the rejection has been withdrawn.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.
Claim Rejections - 35 USC § 103
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 4,6, 11-15, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over AUYEUNG et al. (US 2022/0210446) in view of Holcomb et al. (US 2018/0115776 A1) and further in view of Ma et al. (US 2023/0319314 A1 ).
Regarding claim 1, AUYEUNG discloses a method of coding video data([see in Fig. 11]-in fig. 11 shows a method of video coding), the method comprising: obtaining input data, wherein the input data includes one or more of predicted video data, reconstructed video data, quantization parameter data, boundary strength data, or prediction mode data([see in Fig. 11]-deblocked picture; also shows in [fig. 10]-; DRNLF filter (1010) receives the output of the deblocking filter (1001) that shown by a deblocked picture (1011) and also receives a quantization parameter (QP) map of reconstructed picture. The QP map includes quantization parameters of blocks in the reconstructed picture. The DRNLF filter (1010) can output a picture that is shown by filtered picture (1019) with improved quality, and the filtered picture (1019) is fed to the SAO filter (1002) for further filtering processes).
However, AUYEUNG does not disclose explicitly converting the input data from an input domain to a transform domain to generate converted video data, wherein the input domain is a YUV domain and the transform domain is a non-YUV domain.
In an analogous art, Holcomb discloses converting the input data from an input domain to a transform domain to generate converted video data([see in Fig. 5a]- FIG. 5a, to reconstruct residual values, in the scaler/inverse transformer (535), a scaler/inverse quantizer performs inverse scaling and inverse quantization on the quantized transform coefficients. When the transform stage has not been skipped, an inverse frequency transformer performs an inverse frequency transform, producing blocks of reconstructed prediction residual values or sample values. If the transform stage has been skipped, the inverse frequency transform is also skipped. In this case, the scaler/inverse quantizer can perform inverse scaling and inverse quantization on blocks of prediction residual data (or sample value data), producing reconstructed values. When residual values have been encoded/signaled, the video encoder (340) combines reconstructed residual values with values of the prediction (558) (e.g., motion-compensated prediction values, intra-picture prediction values) to form the reconstruction (538)), wherein the input domain is a YUV domain([See in Fig. 8]-YUV 4:2:0 format) and the transform domain is a non-YUV domain([para 0191]- non-YUV chroma sampling forma). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the technique of Holcomb to the modified system of AUYEUNG an approaches to delivering video in a chroma sampling format with a higher chroma sampling rate (such as a YUV 4:4:4 format) using a video encoder and decoder that operate on video in another chroma sampling format with a lower chroma sampling rate (such as YUV 4:2:0) to reduce the bit rate of digital video [Holcomb; abstract].
However, the combination of AUYEUNG and Holcomb do not exclusively disclose applying a neural network (NN)-based in-loop filter (ILF) to the converted video data to generate filtered video data, wherein applying the NN-based ILF comprises applying the NN based ILF to separate luma and chroma branches of NN models.
In an analogous art, Ma discloses applying a neural network (NN)-based in-loop filter (ILF) to the converted video data to generate filtered video data([abstract]- applying a trained neural network based in-loop filter to the reconstructed picture frame by: converting a first resolution of the samples of the at least one of the first and the second chroma components to a second resolution of the samples of the luma component when the first resolution is different from the second resolution), wherein applying the NN-based ILF comprises applying the NN based ILF to separate luma and chroma branches of NN models([]abstract; [para 009-0010]- applying a trained neural network based in-loop filter to the reconstructed picture frame by: converting a first resolution of the samples of the at least one of the first and the second chroma components to a second resolution of the samples of the luma component when the first resolution is different from the second resolution; concatenating samples of at least one of the first and the second chroma components with the luma component); converting the filtered video data from the transform domain to the input domain([para 0180]- converting a first resolution of the samples of the at least one of the first and the second chroma components to a second resolution of the samples of the luma component). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the technique of Ma to the modified system of AUYEUNG and Holcomb to methods on improving the coding efficiency of video coding and compression, including improving the coding efficiency by applying neural network technique on video coding [ Ma; para 0008].
Regarding claim 4, AUYEUNG discloses wherein converting the input data comprises one of: converting the reconstructed video data in a form of a color space conversion, converting the reconstructed video data in a spatial domain with each component being transformed separately, or converting the reconstructed video data across multiple temporal entities of the reconstructed video data([see in Fig. 12]- wherein: the input domain is a YUV domain, the method further comprises applying a wavelet transform to the YUV domain for each component to decompose the reconstructed video data into a plurality of frequency bands, and the transform domain is a decomposed signal domain. a color space conversion"; " ... each component being transformed separately).
Regarding claim 6, AUYEUNG discloses wherein a transform kernel size of the neural network based in-loop filter ranges from 2x2 to KxK where K is divisible by both a height Hand a width W of a filtering block([see in Fig. 13 and para 0132]- a transform kernel size of the neural network-based in-loop filter ranges from 2x2 to KxK).
Regarding claim 11, AUYEUNG discloses wherein applying the NN-based ILF comprises applying different transform kernel sizes for luma and chroma([see in Fig. 11]- IG. 11 shows a block diagram of a DRNLF filter (1100) in some examples. The DRNLF filter (1100) can be used in the place of the DRNLF filter (1010) in an example. The DRNLF filter (1100) includes a QP map quantizer (1110), a pre-processing module (1120), a main processing module (1130) and a post processing module (1140) coupled together as shown in FIG. 11. The main processing module (1130) includes a patch fetcher (1131), a patch based DRNLF kernel processing module (1132) and a patch reassembler (1133) coupled together as shown in FIG. 11; [0017;0119]).
Regarding claim 12, AUYEUNG discloses wherein the input domain is a Y'CbCr domain and the transform domain is an RGB domain ([para 0117 and 0119]- the input domain YUV and the transform domain is an RGB domain")).
Regarding claim 13, AUYEUNG discloses wherein coding comprises decoding ([see in Fig. 4]-a decoder).
Regarding claim 14, AUYEUNG discloses wherein coding comprises encoding([see in Fig. 4]-encoder).
Regarding claim 15, the claim is interpreted and rejected for the same reason as set forth in claim 1. Hence; all limitations for device claim 15 have been met in method claim 1.
Regarding claim 18, the claim is interpreted and rejected for the same reason as set forth in claim 4.
Regarding claim 20, the claim is interpreted and rejected for the same reason as set forth in claim 1. Hence; all limitations for claim 20 have been met in method claim 1.
Claims 5 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over AUYEUNG in view of Holcomb and Ma as applied to claim 1 above and further in of Crandall et al. ( US 2010/0322305).
Regarding claim 5, the combination of AUYEUNG, Holcomb and Ma do not explicitly disclose wherein: the input domain is a YUV domain, the method further comprises applying a wavelet transform to the YUV domain for each component to decompose the reconstructed video data into a plurality of frequency bands, and the transform domain is a decomposed signal domain.
In an analogous art, Crandall discloses wherein: the input domain is a YUV domain, the method further comprises applying a wavelet transform to the YUV domain for each component to decompose the reconstructed video data into a plurality of frequency bands, and the transform domain is a decomposed signal domain([abstract]- A dynamically-scaled wavelet transform (104) is applied to the data in the YUV domain by estimating a maximum resulting output value of the wavelet transform, and scaling wavelet coefficients responsive to the estimated output value). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the technique of Crandall to the modified system of AUYEUNG, Holcomb and Ma method to a encoding of video streams to achieve full screen real-time playback of high quality movies using a conventional desktop computer system [Crandall; abstract].
Regarding claim 19, the claim is interpreted and rejected for the same reason as set forth in claim 5.
Claims 7, 9, 10 are rejected under 35 U.S.C. 103 as being unpatentable over AUYEUNG in view of Holcomb and Ma as applied to claim 1 above and further in of Birendra et al.(NPL- Multi-stage Locally and Long-range Correlated Feature Fusion for Learned In-loop Filter in VVC).
Regarding claim 7, the combination of AUYEUNG, Holcomb and Ma do not explicitly disclose wherein the method further comprises applying a discrete cosine transform to the reconstructed video data.
In an analogous art, Birendra discloses wherein applying the NN-based ILF comprises applying the NN-based ILF to separate luma and chroma branches of NN models ([DCT Input; section Ill]- Proposed Method page 2 column 2: " ... OCT-input consists of OCT transformed representation of corresponding reconstructed picture, partition and prediction image). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to provide the technique of Birendra to the modified system of AUYEUNG, Holcomb and Ma in obtaining better feature by exploiting locally correlated spatial feature in the pixel domain as well as long range correlated spectral feature in the discrete cosine transform (DCT) domain. In particular, we utilized CNN- feature from DCT transformed input to extract high-frequency components and induce long-range correlation into the spatial CNN- feature by employing multi-stage feature fusion. One experimental result shows that the proposed approach achieves significant coding improvements np to 9.70% on average Bjontegaard Delta (BD)Bitrate savings under AI configurations for lama (Y) components [Abstract; Birendra].
Regarding claim 9, Birendra discloses further comprising adjusting a number of output channels before a pixel shuffle([shuffle; section A. Overview of our CNN-based in-loop filter page 3 column 1:]- the pixel shuffle layer assembles this 4-channel output of size (S/2, S/2) into a single channel feature of the original size (S, SJ to obtain a final clean picture).
Regarding claim 10, Birendra discloses at least one of down-sampling or rearranging the reconstructed video data so that the reconstructed video data is in a down-sampled or rearranged domain ([section Ill. Proposed Method page 3 column 1]- To alleviate the computational complexity, we pixel unshuffled all images types ..... to create four channels for each of size (S/2); and applying a transform to the reconstructed video data in the down-sampled or rearranged domain so that the reconstructed video data is in the transform domain for filtering ([section Ill. Proposed Method page 3 column 1]- To alleviate the computational complexity, we pixel unshuffled all images types to create four channels for each of size (S/2).
Citation of Pertinent Prior Art
The prior art are made of record and not relied upon but considered pertinent to applicant’s disclosure:
1. Wang et al. US 2022/0215593 A1; discloses techniques for filtering decoded pictures, which may be distorted. The filtering process may be based on neural network techniques.
2. ZOU et al., US 2023/0169372 A1, discloses multimedia transport and neural networks.
3. Li et. al., US 2022/0329836 A1, discloses provide one or more neural network (NN) filter models trained as part of an in-loop filtering technology or filtering technology used in a post-processing stage for reducing the distortion incurred during compression.
4. Li et al., US 2023/0007246 A1, discloses applying a neural network (NN) filter to an unfiltered sample of a video unit to generate a filtered sample.
5. LAINEMA et al., US 2024/0121387 A1, discloses multimedia transport and neural networks.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MD NAZMUL HAQUE whose telephone number is (571)272-5328. The examiner can normally be reached IFW.
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, David Czekaj can be reached at 5712727327. 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.
/MD N HAQUE/Primary Examiner, Art Unit 2487
Prosecution Insights