US 12,439,092 B2
Network based image filtering for video coding
Wei Chen, San Diego, CA (US); Xiaoyu Xiu, San Diego, CA (US); Yi-Wen Chen, San Diego, CA (US); Hong-Jheng Jhu, San Diego, CA (US); Che-Wei Kuo, 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 Jun. 2, 2023, as Appl. No. 18/205,475.
Application 18/205,475 is a continuation of application No. PCT/US2021/062061, filed on Dec. 6, 2021.
Claims priority of provisional application 63/121,822, filed on Dec. 4, 2020.
Prior Publication US 2023/0328293 A1, Oct. 12, 2023
Int. Cl. H04N 19/80 (2014.01); G06N 3/045 (2023.01); G06N 3/0464 (2023.01); G06T 3/4046 (2024.01); H04N 19/124 (2014.01); H04N 19/42 (2014.01); G06N 3/048 (2023.01)
CPC H04N 19/80 (2014.11) [G06N 3/045 (2023.01); G06N 3/0464 (2023.01); G06T 3/4046 (2013.01); H04N 19/124 (2014.11); H04N 19/42 (2014.11); G06N 3/048 (2023.01)] 19 Claims
OG exemplary drawing
 
1. A method for image filtering in video coding, comprising:
loading a plurality of input patches associated with a current image to be coded, wherein the plurality of input patches comprise a first input patch with a first resolution, a second input patch with a second resolution, and a third input patch with a third resolution; and
in response to determining that one resolution in the first resolution, the second resolution, and the third resolution is different from the other two resolutions, adjusting the first resolution, the second resolution, and the third resolution at one region of a plurality of regions;
wherein the one region of a plurality of regions comprises a first region; the first region comprises a plurality of input layers receiving the plurality of input patches before a neural network for image filtering and a plurality of output layers outputting a plurality of output patches after the neural network;
wherein the method further comprising:
loading a plurality of quantization parameter (QP) map (QpMap) values at a plurality of QpMap channels, wherein the plurality of QpMap values comprise a first QpMap value at a first QpMap channel, a second QpMap value at a second QpMap channel, and a third QpMap value at a third QpMap channel; and
adjusting the first QpMap value, the second QpMap value, and the third QpMap value so that the first QpMap value, the second QpMap value, and the third QpMap value are within a dynamic range;
wherein the first QpMap value, the second QpMap value, and the third QpMap value are evenly distributed at different positions of the dynamic range.