LiZIP: An Auto-Regressive Compression Framework for LiDAR Point Clouds

TL;DR

LiZIP is a neural predictive coding-based compression framework that significantly reduces LiDAR point cloud data size, outperforming existing methods in efficiency and generalization, thus facilitating real-time autonomous vehicle data processing.

Contribution

The paper introduces LiZIP, a lightweight near-lossless compression method using neural predictive coding with a compact MLP, offering superior compression ratios and generalization without retraining.

Findings

LiZIP achieves 7.5%-14.8% smaller files than LASzip.

LiZIP outperforms Google Draco by 8.8%-11.3%.

LiZIP generalizes well to unseen datasets without retraining.

Abstract

The massive volume of data generated by LiDAR sensors in autonomous vehicles creates a bottleneck for real-time processing and vehicle-to-everything (V2X) transmission. Existing lossless compression methods often force a trade-off: industry standard algorithms (e.g., LASzip) lack adaptability, while deep learning approaches suffer from prohibitive computational costs. This paper proposes LiZIP, a lightweight, near-lossless zero-drift compression framework based on neural predictive coding. By utilizing a compact Multi-Layer Perceptron (MLP) to predict point coordinates from local context, LiZIP efficiently encodes only the sparse residuals. We evaluate LiZIP on the NuScenes and Argoverse datasets, benchmarking against GZip, LASzip, and Google Draco (configured with 24-bit quantization to serve as a high-precision geometric baseline). Results demonstrate that LiZIP consistently achieves superior compression ratios across varying environments. The proposed system achieves a 7.5%-14.8% reduction in file size compared to the industry-standard LASzip and outperforms Google Draco by 8.8%-11.3% across diverse datasets. Furthermore, the system demonstrates generalization capabilities on the unseen Argoverse dataset without retraining. Against the general purpose GZip algorithm, LiZIP achieves a reduction of 38%-48%. This efficiency offers a distinct advantage for bandwidth constrained V2X applications and large scale cloud archival.