US 11,659,185 B2
Matrix-based intra prediction using upsampling
Zhipin Deng, Beijing (CN); Kai Zhang, San Diego, CA (US); Li Zhang, San Diego, CA (US); Hongbin Liu, Beijing (CN); and Jizheng Xu, San Diego, CA (US)
Assigned to BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., Beijing (CN); and BYTEDANCE INC., Los Angeles, CA (US)
Filed by Beijing Bytedance Network Technology Co., Ltd., Beijing (CN); and Bytedance Inc., Los Angeles, CA (US)
Filed on Sep. 20, 2021, as Appl. No. 17/479,360.
Application 17/479,360 is a continuation of application No. PCT/CN2020/091542, filed on May 21, 2020.
Claims priority of application No. PCT/CN2019/087987 (WO), filed on May 22, 2019.
Prior Publication US 2022/0007029 A1, Jan. 6, 2022
Int. Cl. H04N 19/132 (2014.01); G06F 7/78 (2006.01); H04N 19/176 (2014.01); H04N 19/105 (2014.01); H04N 19/159 (2014.01); G06F 17/16 (2006.01)
CPC H04N 19/132 (2014.11) [G06F 7/78 (2013.01); G06F 17/16 (2013.01); H04N 19/105 (2014.11); H04N 19/159 (2014.11); H04N 19/176 (2014.11)] 18 Claims
OG exemplary drawing
 
1. A method of video processing, comprising:
determining, for a conversion between a video block of a video and a bitstream of the video, that a first intra mode is applied on the video block of the video, wherein the first intra mode includes a matrix vector multiplication operation and followed by an upsampling operation to generate prediction samples for the video block; and
performing the conversion based on the prediction samples;
wherein the upsampling operation comprises a horizontal upsampling operation and a vertical upsampling operation, and the horizontal upsampling operation and the vertical upsampling operation are performed in a fixed order; and
the prediction samples are determined according to ((upHor−dX)*predSamples[xHor][yHor]+dX*predSamples[xHor+upHor][yHor]+offsetHor)/upHor in the horizontal upsampling operation, and
the prediction samples are determined according to ((upVer−dY)*predSamples[xVer][yVer]+dY*predSamples[xVer][yVer+upVer]+offsetVer)/upVer in the vertical upsampling operation;
wherein upHor is a function of a width of the video block and a pre-defined value based on the width and a height of the video block,
wherein upVer is a function of the height of the video block and the pre-defined value based on the width and the height of the video block,
wherein offsetHor and offsetVer are integers,
wherein 1 <=dX<=upHor−1,
wherein 1 <=dY<=upVer−1, and
wherein xHor are positions based on the upHor and yHor are positions based on the upVer.