US 12,444,090 B2
Point cloud attribute prediction method and apparatus, and related device
Wenjie Zhu, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Nov. 17, 2022, as Appl. No. 17/989,523.
Application 17/989,523 is a continuation of application No. PCT/CN2022/080809, filed on Mar. 15, 2022.
Claims priority of application No. 202110655607.3 (CN), filed on Jun. 11, 2021.
Prior Publication US 2023/0082456 A1, Mar. 16, 2023
Int. Cl. G06T 9/00 (2006.01); H04N 19/105 (2014.01); H04N 19/169 (2014.01)
CPC G06T 9/001 (2013.01) [H04N 19/105 (2014.11); H04N 19/169 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A point cloud attribute prediction method, performed by a computing device, the method comprising:
decoding a point cloud code stream to obtain decoded points in a point cloud;
determining a target association relationship, the target association relationship including an association relationship between neighbor point parameters;
obtaining the neighbor point parameters according to the target association relationship, the neighbor point parameters including at least one of a quantity N of candidate points of a current point, a quantity K of neighbor points, and a preset distance d between the neighbor point and the current point, both N and K being positive integers, and d being a positive number;
selecting at least one neighbor point of the current point from the decoded points according to the neighbor point parameters; and
determining a predicted value of attribute information of the current point according to attribute information of the at least one neighbor point of the current point,
wherein:
the association relationship between the neighbor point parameters includes a mathematical operation relationship between a reference parameter and a non-reference parameter in the neighbor point parameters, the reference parameter being one of the quantity N of candidate points, the quantity K of neighbor points, and the preset distance d, and the non-reference parameter being a parameter in the neighbor point parameters other than the reference parameter.