US 12,238,343 B2
Video coding with neural network based in-loop filtering
Tsung-Chuan Ma, Beijing (CN); Wei Chen, Beijing (CN); Xiaoyu Xiu, Beijing (CN); Yi-Wen Chen, Beijing (CN); Hong-Jheng Jhu, Beijing (CN); Che-Wei Kuo, Beijing (CN); Xianglin Wang, Bejing (CN); 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. 31, 2023, as Appl. No. 18/193,763.
Application 18/193,763 is a continuation of application No. PCT/US2021/052915, filed on Sep. 30, 2021.
Claims priority of provisional application 63/086,538, filed on Oct. 1, 2020.
Prior Publication US 2023/0319314 A1, Oct. 5, 2023
Int. Cl. H04N 19/82 (2014.01); H04N 19/186 (2014.01)
CPC H04N 19/82 (2014.11) [H04N 19/186 (2014.11)] 18 Claims
OG exemplary drawing
 
1. A method of decoding video data, comprising:
reconstructing, from a video bitstream, a picture frame that includes a luma component, a first chroma component, and a second chroma component, and
applying a trained neural network based in-loop filter to the reconstructed picture frame by performing operations comprising:
concatenating samples of at least one of the first and the second chroma components with the luma component to create concatenated samples; and
processing the concatenated samples using a convolutional neural network
wherein the trained neural network based in-loop filter has been trained to obtain model parameters by reducing difference between output reconstructed picture frames from the convolutional neural network and corresponding ground-truth picture frames,
wherein applying the trained neural network based in-loop filter to the reconstructed picture frame further comprises:
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 of the at least one of the first and the second chroma components is different from the second resolution of the luma component; and
reconverting the samples of the at least one of the first and the second chroma components processed by the convolutional neural network from the second resolution back to the first resolution.