Title:
POINT CLOUD ATTRIBUTE PREDICTION, ENCODING, AND DECODING METHOD AND DEVICE BASED ON NEIGHBOR WEIGHT OPTIMIZATION
Document Type and Number:
WIPO Patent Application WO/2021/023206
Kind Code:
A1
Abstract:
Disclosed are a point cloud attribute prediction method, encoding method, decoding method, and device based on neighbor weight optimization, said point cloud attribute prediction method comprising: determining K nearest neighbor points of a current point; determining the optimized weights of the K nearest neighbor points of the current point according to the coordinates of the current point and the coordinates of the K nearest neighbor points of the current point; determining the attribute prediction value of the current point according to the optimized weights of the K nearest neighbor points of the current point. In the present invention, when the attributes of each point are predicted, the attribute prediction value of the current point is calculated according to the optimized weights of the K nearest neighbor points of the current point, making full use of the geometric information and attribute information relevance of the point cloud, increasing the accuracy of attribute prediction, and improving point cloud attribute encoding and decoding performance.
Inventors:
LI GE (CN)
ZHANG QI (CN)
WANG JING (CN)
SHAO YI TING (CN)
GAO WEN (CN)
ZHANG QI (CN)
WANG JING (CN)
SHAO YI TING (CN)
GAO WEN (CN)
Application Number:
PCT/CN2020/107021
Publication Date:
February 11, 2021
Filing Date:
August 05, 2020
Export Citation:
Assignee:
UNIV PEKING SHENZHEN GRADUATE SCHOOL (CN)
International Classes:
H04N19/13; H04N19/124; H04N19/147; H04N19/42; H04N19/593
Foreign References:
| CN110418135A | 2019-11-05 | |||
| CN110572655A | 2019-12-13 | |||
| CN110708560A | 2020-01-17 | |||
| US20190080483A1 | 2019-03-14 | |||
| US20170214943A1 | 2017-07-27 | |||
| CN109166160A | 2019-01-08 |
Attorney, Agent or Firm:
BEIJING JWT INTELLECTUAL PROPERTY CO., LTD. (CN)
Download PDF: