US 12,309,364 B2
System and method for applying neural network based sample adaptive offset for video coding
Wei Chen, San Diego, CA (US); Xiaoyu Xiu, San Diego, CA (US); Che-Wei Kuo, Beijing (CN); Yi-Wen Chen, San Diego, CA (US); Hong-Jheng Jhu, Beijing (CN); Xianglin Wang, San Diego, CA (US); and Bing Yu, Beijing (CN)
Assigned to BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD., Beijing (CN)
Filed by Beijing Dajia Internet Information Technology Co., Ltd., Beijing (CN)
Filed on Mar. 11, 2022, as Appl. No. 17/692,298.
Claims priority of provisional application 63/171,979, filed on Apr. 7, 2021.
Prior Publication US 2022/0337824 A1, Oct. 20, 2022
Int. Cl. H04N 19/117 (2014.01); H04N 19/14 (2014.01); H04N 19/176 (2014.01); H04N 19/42 (2014.01); H04N 19/82 (2014.01); H04N 19/159 (2014.01)
CPC H04N 19/117 (2014.11) [H04N 19/14 (2014.11); H04N 19/176 (2014.11); H04N 19/42 (2014.11); H04N 19/82 (2014.11); H04N 19/159 (2014.11)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for applying neural network based sample adaptive offset (SAO) for video coding, comprising:
classifying, by a video processor, reconstructed samples of a reconstructed block into a set of categories based on neural network based in-loop filtering (NNLF), wherein the reconstructed block comprises a reconstructed version of a video block of a video frame from a video;
determining, by the video processor, a set of offsets for the set of categories based on the classification of the reconstructed samples; and
responsive to the NNLF being performed on the reconstructed block, performing, by the video processor, SAO filtering on NNLF filtered samples based on the set of offsets, wherein the NNLF filtered samples are generated from the reconstructed samples using the NNLF,
wherein classifying the reconstructed samples into the set of categories further comprises:
performing a texture edge classification on the reconstructed samples to classify the reconstructed samples into a set of texture edge categories, and
wherein performing the texture edge classification on the reconstructed samples to classify the reconstructed samples into the set of texture edge categories comprises:
performing the NNLF on the reconstructed samples to generate the NNLF filtered samples; and
classifying each reconstructed sample into a corresponding texture edge category based on a category threshold and a sample difference between the reconstructed sample and a corresponding NNLF filtered sample of the reconstructed sample.