Towards Practical Lossless Neural Compression for LiDAR Point Clouds

2026-03-26

AI Summary

This work addresses the limitations of existing neural compression methods for high-precision LiDAR point clouds, which suffer from inefficiency, slow speed, and suboptimal performance due to extreme geometric sparsity. To overcome these challenges, the authors propose a compact representation framework that enhances contextual modeling through geometric re-densification and cross-scale feature propagation. A key innovation is the design of an integer-only inference pipeline that guarantees bit-exact consistency across platforms and prevents entropy coding collapse. The method supports predictive lossless coding, achieving near real-time encoding and decoding speeds while maintaining competitive compression ratios, thereby significantly outperforming current neural compression approaches.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• LiDAR point clouds
• lossless compression
• sparsity
• context modeling
• neural compression

Innovation

• lossless neural compression
• LiDAR point clouds
• geometry re-densification
• cross-scale feature propagation
• integer-only inference