Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-05 · 48 (5) · 5371-5387
DOI: 10.1109/tpami.2025.3650590 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-05. Verfasst von Bojun Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Major Science and Technology Project.
Abstract (Originalsprache)
We propose Next Bit Prediction (NBP), a unified framework that simultaneously addresses lossless compression and lossy reconstruction of 3D point cloud geometry through a next-bit probability estimation paradigm. Our key insight is that both lossless compression and lossy reconstruction fundamentally rely on accurate probability estimation of geometric symbols, though targeting different metrics. Lossless compression minimizes bitrate via precise symbol distribution prediction, while lossy reconstruction enhances reconstruction fidelity through probability-guided geometry refinement. Recognizing that point clouds become sparser with increasing bit depth, NBP introduces two key technical innovations. For more significant bits, where the point density is higher, we develop a multi-stage Occupancy Probability Estimation (OPE) mechanism to estimate the probability distribution of occupancy status across multiple iteration stages, with each stage supporting either lossless or lossy mode. For less significant bits that focus on point placement, a Disentangled Probability Estimation (DPE) module is proposed to handle density information and binary residuals, simultaneously enabling lossless compression and facilitating probability-driven coordinate refinement for high-quality lossy reconstruction. Extensive experiments demonstrate the advantages of NBP, including low complexity, progressive coding, and superior coding efficiency, achieving state-of-the-art results both quantitatively and qualitatively.
Förderung
- National Major Science and Technology Project
Zitieren
APA
Liu, B., Ma, Y., Li, L., Liu, D., Li, Z., & Li, H. (2026). Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(5), 5371-5387. https://doi.org/10.1109/tpami.2025.3650590
Vancouver
Liu B, Ma Y, Li L, Liu D, Li Z, Li H. Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(5):5371-5387. doi:10.1109/tpami.2025.3650590
BibTeX
@article{Liu2026,
author = {Liu, Bojun and Ma, Yangzhi and Li, Li and Liu, Dong and Li, Zhu and Li, Houqiang},
title = {Next Bit Prediction: A Unified Lossless and Lossy Point Cloud Geometry Compression Framework},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {5},
pages = {5371--5387},
doi = {10.1109/tpami.2025.3650590}
}
EUVIMED