Towards Practical Lossless Neural Compression for LiDAR Point Clouds

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Pengpeng, Li, Haoran, Jiang, Runqing, Li, Dingquan, Wang, Jing, Lin, Liang, Guo, Yulan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911546097008640
author Yu, Pengpeng
Li, Haoran
Jiang, Runqing
Li, Dingquan
Wang, Jing
Lin, Liang
Guo, Yulan
author_facet Yu, Pengpeng
Li, Haoran
Jiang, Runqing
Li, Dingquan
Wang, Jing
Lin, Liang
Guo, Yulan
contents LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To address this challenge, we propose a compact representation for efficient predictive lossless coding. Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module iteratively densifies encoded sparse geometry, extracts features at a dense scale, and then sparsifies the features for predictive coding. This module avoids costly computation on highly sparse details while maintaining a lightweight prediction head. Second, the Cross-scale Feature Propagation Module leverages occupancy cues from multiple resolution levels to guide hierarchical feature propagation, enabling information sharing across scales and reducing redundant feature extraction. Additionally, we introduce an integer-only inference pipeline to enable bit-exact cross-platform consistency, which avoids the entropy-coding collapse observed in existing neural compression methods and further accelerates coding. Experiments demonstrate competitive compression performance at real-time speed. Code will be released upon acceptance. Code is available at https://github.com/pengpeng-yu/FastPCC.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25260
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Practical Lossless Neural Compression for LiDAR Point Clouds
Yu, Pengpeng
Li, Haoran
Jiang, Runqing
Li, Dingquan
Wang, Jing
Lin, Liang
Guo, Yulan
Computer Vision and Pattern Recognition
LiDAR point clouds are fundamental to various applications, yet the extreme sparsity of high-precision geometric details hinders efficient context modeling, thereby limiting the compression speed and performance of existing methods. To address this challenge, we propose a compact representation for efficient predictive lossless coding. Our framework comprises two lightweight modules. First, the Geometry Re-Densification Module iteratively densifies encoded sparse geometry, extracts features at a dense scale, and then sparsifies the features for predictive coding. This module avoids costly computation on highly sparse details while maintaining a lightweight prediction head. Second, the Cross-scale Feature Propagation Module leverages occupancy cues from multiple resolution levels to guide hierarchical feature propagation, enabling information sharing across scales and reducing redundant feature extraction. Additionally, we introduce an integer-only inference pipeline to enable bit-exact cross-platform consistency, which avoids the entropy-coding collapse observed in existing neural compression methods and further accelerates coding. Experiments demonstrate competitive compression performance at real-time speed. Code will be released upon acceptance. Code is available at https://github.com/pengpeng-yu/FastPCC.
title Towards Practical Lossless Neural Compression for LiDAR Point Clouds
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.25260