	US 12,439,082 B2
	Methods for instance-based mesh coding
Thuong Nguyen Canh, San Bruno, CA (US); Xiang Zhang, Sunnyvale, CA (US); Xiaozhong Xu, State College, PA (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 May 4, 2023, as Appl. No. 18/312,338.
Claims priority of provisional application 63/392,409, filed on Jul. 26, 2022.
Prior Publication US 2024/0040148 A1, Feb. 1, 2024
Int. Cl. H04N 19/00 (2014.01); H04N 19/103 (2014.01); H04N 19/17 (2014.01); H04N 19/44 (2014.01); H04N 19/597 (2014.01)

CPC H04N 19/597 (2014.11) [H04N 19/103 (2014.11); H04N 19/17 (2014.11); H04N 19/44 (2014.11)]

20 Claims

1. A method for video decoding, the method performed by at least one processor and comprising:

obtaining an input mesh corresponding to volumetric data of at least one three-dimensional (3D) visual content;

partitioning the input mesh corresponding to the volumetric data into a plurality of submeshes, each of the submeshes comprising a respective one of instances of objects;

determining a similarity between at least two of the instances of objects;

grouping the plurality of submeshes based on the determined similarity; and

decoding the volumetric data based on the grouping of the plurality of submeshes.