US 11,943,444 B2
Restricted upsampling process in matrix-based intra prediction
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 Aug. 12, 2022, as Appl. No. 17/887,297.
Application 17/887,297 is a continuation of application No. 17/480,208, filed on Sep. 21, 2021, granted, now 11,451,784.
Application 17/480,208 is a continuation of application No. PCT/CN2020/092906, filed on May 28, 2020.
Claims priority of application No. PCT/CN2019/089590 (WO), filed on May 31, 2019.
Prior Publication US 2023/0039865 A1, Feb. 9, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 19/132 (2014.01); G06F 17/16 (2006.01); H04N 19/105 (2014.01); H04N 19/159 (2014.01); H04N 19/176 (2014.01)
CPC H04N 19/132 (2014.11) [G06F 17/16 (2013.01); H04N 19/105 (2014.11); H04N 19/159 (2014.11); H04N 19/176 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A method of processing video data, 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 a process in the first intra mode includes a matrix vector multiplication operation followed by an upsampling operation to generate prediction samples for the video block of the video; and
performing the conversion based on the prediction samples,
wherein inputs to the upsampling operation include neighboring reference samples of the video block of the video, and
wherein the process in the first intra mode further includes a downsampling operation prior to the matrix vector multiplication operation based on a size of the video block.