Efficient LiDAR Reflectance Compression via Scanning Serialization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918036155400192 |
|---|---|
| author | Zhu, Jiahao You, Kang Ding, Dandan Ma, Zhan |
| author_facet | Zhu, Jiahao You, Kang Ding, Dandan Ma, Zhan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09433 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient LiDAR Reflectance Compression via Scanning Serialization Zhu, Jiahao You, Kang Ding, Dandan Ma, Zhan Computer Vision and Pattern Recognition Image and Video Processing 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. |
| title | Efficient LiDAR Reflectance Compression via Scanning Serialization |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2505.09433 |