A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding - Part I: Geometry
Lists
Only you see this
Abstract
A universal multiscale conditional coding framework, Unicorn, is proposed to compress the geometry and attribute of any given point cloud. Geometry compression is addressed in Part I of this paper, while attribute compression is discussed in Part II. We construct the multiscale sparse tensors of each voxelized point cloud frame and properly leverage lower-scale priors in the current and (previously processed) temporal reference frames to improve the conditional probability approximation or content-aware predictive reconstruction of geometry occupancy in compression. Unicorn is a versatile, learning-based solution capable of compressing static and dynamic point clouds with diverse source characteristics in both lossy and lossless modes. Following the same evaluation criteria, Unicorn significantly outperforms standard-compliant approaches like MPEG G-PCC, V-PCC, and other learning-based solutions, yielding state-of-the-art compression efficiency while presenting affordable complexity for practical implementations.
BibTeX
@article{wang2025versatile,
author = {Jianqiang Wang and Ruixiang Xue and Jiaxin Li and Dandan Ding and Yi Lin and Zhan Ma},
title = {{A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding - Part I: Geometry}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2025},
url = {https://openreview.net/forum?id=Fj6P7iNx7x},
}Loading related content...