Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Aditya Shibu, Kayvan Karim, Claudio Zito

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.

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

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.
Paper Structure (26 sections, 3 equations, 6 figures, 4 tables)

This paper contains 26 sections, 3 equations, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional and Geometric Methods
  4. General-Purpose Compression
  5. Deep Learning-Based Approaches
  6. The LiZIP compressor
  7. Spatial Organization (Morton Sorting)
  8. Zero-Drift Quantized Compression
  9. Compressing Geometry (Neural Prediction)
  10. Residual Encoding and Byte Shuffling
  11. Entropy Coding
  12. LiZIP File Format
  13. Experimental Results
  14. Experimental Setup
  15. Training Methodology
  16. ...and 11 more sections

Figures (6)

  • Figure 1: System Architecture of the LiZIP Compressor. Raw points are sorted and quantized. Processing occurs in parallel blocks: the first $k$ points (Anchors) initialize the context, while the MLP predicts the rest. Both anchors and residuals are byte-shuffled and entropy coded.
  • Figure 2: Distribution of prediction residuals by the chosen $k=3, H=256$ configuration after neural prediction. Residuals are sharply peaked around zero, which improves entropy coding efficiency.
  • Figure 3: The LiZIP Binary File Format.
  • Figure 4: Ablation Study of LiZIP Compression Stages. The "Waterfall" chart highlights that the Neural Predictor (MLP) is the primary driver of compression (53.2% reduction), distinguishing LiZIP from simple quantization schemes.
  • Figure 5: File Size Compression Breakdown of LiZIP against Baselines on NuScenes Dataset. Linear growth indicates consistent per-frame compression performance across all methods.
  • ...and 1 more figures