US 12,284,349 B2
Adaptive quantization for instance-based mesh coding
Thuong Nguyen Canh, Palo Alto, CA (US); Xiaozhong Xu, State College, PA (US); Xiang Zhang, Sunnyvale, 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 May 5, 2023, as Appl. No. 18/312,675.
Claims priority of provisional application 63/359,749, filed on Jul. 8, 2022.
Prior Publication US 2024/0015289 A1, Jan. 11, 2024
Int. Cl. H04N 19/124 (2014.01); H04N 19/172 (2014.01); H04N 19/184 (2014.01); H04N 19/597 (2014.01)
CPC H04N 19/124 (2014.11) [H04N 19/172 (2014.11); H04N 19/184 (2014.11); H04N 19/597 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A method for video coding, the method performed by at least one processor and comprising:
obtaining an input mesh comprising volumetric data of at least one three-dimensional (3D) visual content;
deriving a plurality of submeshes of the input mesh from a frame of the volumetric data, each of the submeshes comprising a respective one of instances of objects, and at least a first submesh and a second submesh from the plurality of the submeshes overlap each other in the frame;
setting a first bitdepth to the first submesh and a second bitdepth to the second submesh, the first bitdepth being different than the second bitdepth;
quantizing the first submesh and the second submesh based on the first bitdepth and the second bitdepth respectively; and
signaling a result of quantizing the first submesh and the second submesh.