cs.CVNov 12, 2026

SPEM: Scan-Prior Entropy Modeling for LiDAR Point Cloud Compression

Authors: Bojun Liu, Yangzhi Ma, Jie Li, Dong Liu, Li Li

Organizations: University of Science and Technology of China

Abstract

LiDAR point clouds exhibit scan-induced spatial regularities that are informative for geometry compression. Existing scan-aware approaches often exploit these regularities by transforming coded geometry into spherical or beam-aligned coordinate systems. However, this couples acquisition priors with geometry representation, altering spatial partitioning and quantization, and potentially preventing exact recovery of the original Cartesian geometry. We argue that acquisition priors should guide probability modeling rather than dictate the coding representation. We propose SPEM, a Scan-Prior Entropy Modeling framework that exploits LiDAR scanning regularities within the entropy model without requiring coordinate transformation. We introduce a multi-frequency spherical rotary positional encoding that captures scan-aligned spatial relationships in both backbone self-attention and decoded-context retrieval. Building upon this encoding, we develop a decoded-memory autoregressive predictor that efficiently exploits previously decoded occupancy information through reusable key/value caches. Experiments demonstrate state-of-the-art performance in both lossy and lossless LiDAR geometry compression, highlighting the effectiveness of scan-prior modeling across different coordinate representations.

Figures & tables

Explore similar work

CardsList
  1. Towards Practical Lossless Neural Compression for LiDAR Point Clouds

    Mar 26, 2026Pengpeng Yu, Haoran Li, Runqing Jiang +4Point Cloud Compression

  2. Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression

    May 18, 2026Chang Sun, Hui Yuan, Shiqi Jiang +3Point Cloud CompressionPredictive Coding

  3. Efficient LiDAR Reflectance Compression via Scanning Serialization

    May 14, 2025Jiahao Zhu, Kang You, Dandan Ding +1Point Cloud Compression