US 12,348,724 B2
Fusion of video prediction modes
Xinwei Li, San Mateo, CA (US); Ru-Ling Liao, San Mateo, CA (US); Jie Chen, San Mateo, CA (US); and Yan Ye, San Mateo, CA (US)
Assigned to Alibaba Innovation Private Limited, Singapore (SG)
Filed by Alibaba Innovation Private Limited, Singapore (SG)
Filed on Dec. 23, 2022, as Appl. No. 18/146,172.
Claims priority of provisional application 63/296,533, filed on Jan. 5, 2022.
Prior Publication US 2023/0217026 A1, Jul. 6, 2023
Int. Cl. H04N 19/132 (2014.01); H04N 19/105 (2014.01); H04N 19/176 (2014.01); H04N 19/182 (2014.01); H04N 19/186 (2014.01); H04N 19/46 (2014.01)
CPC H04N 19/132 (2014.11) [H04N 19/105 (2014.11); H04N 19/176 (2014.11); H04N 19/182 (2014.11); H04N 19/186 (2014.11); H04N 19/46 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A video processing method, comprising:
generating a plurality of predicted chroma samples associated with a pixel, by using a plurality of chroma intra prediction modes respectively; and
determining a first predicted chroma sample in a first predicted chroma block, based on a weighted sum of the plurality of predicted chroma samples,
wherein the determining of the first predicted chroma sample based on the weighted sum of the plurality of predicted chroma samples comprises:
in response to the first predicted chroma sample being associated with an I slice, determining a plurality of weights, based on chroma intra prediction modes used for predicting one or more neighboring blocks of the first predicted chroma block, or
in response to the first predicted chroma sample being associated with a B slice or a P slice, determining the plurality of weights to have equal values; and
determining the weighted sum of the plurality of predicted chroma samples by applying the determined plurality of weights to the plurality of predicted chroma samples, respectively.