Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2308.12535 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929237510848512 |
|---|---|
| author | Luo, Ao Song, Linxin Nonaka, Keisuke Unno, Kyohei Sun, Heming Goto, Masayuki Katto, Jiro |
| author_facet | Luo, Ao Song, Linxin Nonaka, Keisuke Unno, Kyohei Sun, Heming Goto, Masayuki Katto, Jiro |
| contents | In recent years, the task of learned point cloud compression has gained prominence. An important type of point cloud, the spinning LiDAR point cloud, is generated by spinning LiDAR on vehicles. This process results in numerous circular shapes and azimuthal angle invariance features within the point clouds. However, these two features have been largely overlooked by previous methodologies. In this paper, we introduce a model-agnostic method called Spherical-Coordinate-based learned Point cloud compression (SCP), designed to leverage the aforementioned features fully. Additionally, we propose a multi-level Octree for SCP to mitigate the reconstruction error for distant areas within the Spherical-coordinate-based Octree. SCP exhibits excellent universality, making it applicable to various learned point cloud compression techniques. Experimental results demonstrate that SCP surpasses previous state-of-the-art methods by up to 29.14% in point-to-point PSNR BD-Rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_12535 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SCP: Spherical-Coordinate-based Learned Point Cloud Compression Luo, Ao Song, Linxin Nonaka, Keisuke Unno, Kyohei Sun, Heming Goto, Masayuki Katto, Jiro Computer Vision and Pattern Recognition Image and Video Processing In recent years, the task of learned point cloud compression has gained prominence. An important type of point cloud, the spinning LiDAR point cloud, is generated by spinning LiDAR on vehicles. This process results in numerous circular shapes and azimuthal angle invariance features within the point clouds. However, these two features have been largely overlooked by previous methodologies. In this paper, we introduce a model-agnostic method called Spherical-Coordinate-based learned Point cloud compression (SCP), designed to leverage the aforementioned features fully. Additionally, we propose a multi-level Octree for SCP to mitigate the reconstruction error for distant areas within the Spherical-coordinate-based Octree. SCP exhibits excellent universality, making it applicable to various learned point cloud compression techniques. Experimental results demonstrate that SCP surpasses previous state-of-the-art methods by up to 29.14% in point-to-point PSNR BD-Rate. |
| title | SCP: Spherical-Coordinate-based Learned Point Cloud Compression |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2308.12535 |