English

Efficient LiDAR Reflectance Compression via Scanning Serialization

Computer Vision and Pattern Recognition 2025-05-28 v2 Image and Video Processing

Abstract

Reflectance attributes in LiDAR point clouds provide essential information for downstream tasks but remain underexplored in neural compression methods. To address this, we introduce SerLiC, a serialization-based neural compression framework to fully exploit the intrinsic characteristics of LiDAR reflectance. SerLiC first transforms 3D LiDAR point clouds into 1D sequences via scan-order serialization, offering a device-centric perspective for reflectance analysis. Each point is then tokenized into a contextual representation comprising its sensor scanning index, radial distance, and prior reflectance, for effective dependencies exploration. For efficient sequential modeling, Mamba is incorporated with a dual parallelization scheme, enabling simultaneous autoregressive dependency capture and fast processing. Extensive experiments demonstrate that SerLiC attains over 2x volume reduction against the original reflectance data, outperforming the state-of-the-art method by up to 22% reduction of compressed bits while using only 2% of its parameters. Moreover, a lightweight version of SerLiC achieves > 10 fps (frames per second) with just 111K parameters, which is attractive for real-world applications.

Keywords

Cite

@article{arxiv.2505.09433,
  title  = {Efficient LiDAR Reflectance Compression via Scanning Serialization},
  author = {Jiahao Zhu and Kang You and Dandan Ding and Zhan Ma},
  journal= {arXiv preprint arXiv:2505.09433},
  year   = {2025}
}
R2 v1 2026-06-28T23:33:06.437Z