US 12,288,367 B2
Point cloud geometry compression
Sam Tak Wu Kwong, Kowloon (HK); Xinju Wu, Kowloon (HK); and Shiqi Wang, Kowloon (HK)
Assigned to City University of Hong Kong, Kowloon (HK)
Filed by City University of Hong Kong, Kowloon (HK)
Filed on Aug. 1, 2023, as Appl. No. 18/363,169.
Prior Publication US 2025/0045970 A1, Feb. 6, 2025
Int. Cl. G06T 9/00 (2006.01)
CPC G06T 9/001 (2013.01) [G06T 9/002 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method for learning-based point cloud geometry compression, comprising:
given a source point cloud, regressing an aligned mesh that is driven by a set of parameters from a deformable template mesh;
quantizing the set of parameters into a parameter bitstream;
generating an aligned point cloud from the quantized parameters by mesh manipulation and mesh-to-point-cloud conversion;
extracting features from the source point cloud to provide features of the source point cloud and extracting features from the aligned point cloud to provide features of the aligned point cloud based on sparse tensors comprising coordinates and features, the coordinates being encoded into a coordinate bitstream;
warping the features of the aligned point cloud onto the coordinates of the source point cloud to provide warped features of the aligned point cloud;
obtaining residual features through feature subtraction;
processing the residual features using an entropy model into a residual feature bitstream; and
obtaining a reconstructed point cloud by processing the parameter bitstream, the coordinate bitstream and the residual feature bitstream.