Towards Practical Lossless Neural Compression for LiDAR Point Clouds

TL;DR

This paper introduces a novel neural compression framework for LiDAR point clouds that densifies sparse geometry, leverages multi-scale features, and ensures real-time, bit-exact lossless compression with high efficiency.

Contribution

It proposes a lightweight, predictive lossless coding method with a geometry re-densification and cross-scale feature propagation modules for efficient LiDAR point cloud compression.

Findings

Achieves competitive compression ratios with real-time processing.

Ensures bit-exact cross-platform consistency with integer-only inference.

Reduces redundant feature extraction through hierarchical multi-scale guidance.

Abstract

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.