← Back to Benchmarks
simmediumroboticsmetric · varies

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

Description

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 ut

Source

http://arxiv.org/abs/2603.23162v1