US 12,406,399 B2
Point cloud prediction processing methods and apparatuses, computer, and storage medium
Wenjie Zhu, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Guangdong (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Guangdong (CN)
Filed on Aug. 21, 2023, as Appl. No. 18/236,279.
Application 18/236,279 is a continuation of application No. PCT/CN2022/135899, filed on Dec. 1, 2022.
Claims priority of application No. 202210243498.9 (CN), filed on Mar. 11, 2022.
Prior Publication US 2023/0394711 A1, Dec. 7, 2023
Int. Cl. G06T 9/00 (2006.01); H04N 19/50 (2014.01); H04N 19/60 (2014.01); H04N 19/61 (2014.01)
CPC G06T 9/00 (2013.01) [H04N 19/50 (2014.11); H04N 19/60 (2014.11); H04N 19/61 (2014.11)] 19 Claims
OG exemplary drawing
 
1. A method for point cloud prediction processing, the method comprising:
obtaining an alternative point set of a target point cloud group from M point cloud groups, the M point cloud groups including the target point cloud group, coordinate code words of point cloud points in each of the M point cloud groups being identical after shifting by a grouping shift bit number corresponding to the respective point cloud group;
obtaining prediction reference points associated with a target point cloud point of the point cloud points in the target point cloud group from the alternative point set; and
predicting, by processing circuitry, the target point cloud point based on the prediction reference points, to obtain a target predicted attribute value of the target point cloud point, wherein
when a mean value of quantities of the point cloud points respectively contained in M1 neighboring point cloud groups adjacent to the target point cloud group is greater than a first point quantity threshold, the grouping shift bit number corresponding to the target point cloud group is less than the grouping shift bit numbers corresponding to the M1 neighboring point cloud groups;
when the mean value of the quantities of the point cloud points contained in the M1 neighboring point cloud groups adjacent to the target point cloud group is less than a second point quantity threshold, the grouping shift bit number corresponding to the target point cloud group is greater than the grouping shift bit numbers corresponding to the M1 neighboring point cloud groups;
M1 is a subset of M; and
the first point quantity threshold is greater than the second point quantity threshold.