US 12,236,649 B2
Method and apparatus for calculating distance based weighted average for point cloud coding
Xiang Zhang, Sunnyvale, CA (US); Wen Gao, West Windsor, NJ (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 23, 2022, as Appl. No. 17/751,413.
Claims priority of provisional application 63/208,340, filed on Jun. 8, 2021.
Prior Publication US 2022/0392114 A1, Dec. 8, 2022
Int. Cl. G06K 9/00 (2022.01); G06F 1/03 (2006.01); G06F 5/01 (2006.01); G06F 7/50 (2006.01); G06F 7/535 (2006.01); G06T 9/00 (2006.01)
CPC G06T 9/001 (2013.01) [G06F 1/03 (2013.01); G06F 5/01 (2013.01); G06F 7/50 (2013.01); G06F 7/535 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for point cloud coding, comprising:
determining to use a prediction mode for coding information associated with a current point in a point cloud, the information associated with the current point being predicted in the prediction mode based on one or more neighbor points of the current point;
calculating a sum of weighted attributes of the one or more neighbor points, a first weighted attribute in the weighted attributes being associated with a first neighbor point of the one or more neighbor points and being calculated based on a multiplication of a first attribute associated with the first neighbor point with a first converted weight;
calculating a distance-based weighted average value based on a division of the sum of the weighted attributes by a sum of converted weights associated with the one or more neighbor points; and
determining the information associated with the current point based on the distance-based weighted average value.