US 12,452,406 B2
Method and apparatus for asymmetric blending of predictions of partitioned pictures
Han Gao, San Diego, CA (US); Xin Zhao, Sunnyvale, CA (US); Lien-fei Chen, San Jose, CA (US); and Shan Liu, San Jose, CA (US)
Assigned to TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed by TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed on Nov. 8, 2022, as Appl. No. 17/983,017.
Claims priority of provisional application 63/346,614, filed on May 27, 2022.
Claims priority of provisional application 63/345,329, filed on May 24, 2022.
Prior Publication US 2023/0388484 A1, Nov. 30, 2023
Int. Cl. H04N 19/105 (2014.01); G06T 5/70 (2024.01); G06T 7/11 (2017.01); G06T 7/13 (2017.01); G06V 10/74 (2022.01)
CPC H04N 19/105 (2014.11) [G06T 5/70 (2024.01); G06T 7/11 (2017.01); G06T 7/13 (2017.01); G06V 10/761 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for video decoding, the method comprising:
receiving a video bitstream comprising a current block in a current picture;
identifying a partitioning boundary that divides a picture area of the current picture into a first part and a second part;
determining a first threshold corresponding to the first part and a second threshold corresponding to the second part, wherein at least one of the first threshold and the second threshold comprises a negative value and the negative value indicates displacement;
applying a first blending mask, based on the first threshold to the first part to generate a first blended region, and a second blending mask, based on the second threshold to the second part to generate a second blended region, the first blending mask is different from the second blending mask, and at least one of the first blending mask and the second blending mask is based on weighting values of a certain position (xc, yc) and is given by a ramp function; and
reconstructing an image including a prediction for the picture area comprising the first part and the second part as modified by the first blended region and the second blended region.