A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding – Part I: Geometry
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-01 · 47 (1) · 269-287
DOI: 10.1109/tpami.2024.3462938 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-01. Verfasst von Jianqiang Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 77 Literaturangaben. Gefördert von: Natural Science Foundation of Jiangsu Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
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.
Förderung
- Natural Science Foundation of Jiangsu Province
- National Natural Science Foundation of China
Zitieren
APA
Wang, J., Xue, R., Li, J., Ding, D., Lin, Y., & Ma, Z. (2025). A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding – Part I: Geometry. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(1), 269-287. https://doi.org/10.1109/tpami.2024.3462938
Vancouver
Wang J, Xue R, Li J, Ding D, Lin Y, Ma Z. A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding – Part I: Geometry. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(1):269-287. doi:10.1109/tpami.2024.3462938
BibTeX
@article{Wang2025,
author = {Wang, Jianqiang and Xue, Ruixiang and Li, Jiaxin and Ding, Dandan and Lin, Yi and Ma, Zhan},
title = {A Versatile Point Cloud Compressor Using Universal Multiscale Conditional Coding – Part I: Geometry},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {1},
pages = {269--287},
doi = {10.1109/tpami.2024.3462938}
}
EUVIMED