Research map / Point clouds / Point cloud classification
Point Cloud Compression with Sibling Context and Surface Priors
Zhili Chen, Zian Qian, Sukai Wang, Qifeng Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add siblings' children context (ablation) | Ours entropy model · KITTI Odometry (ablation) | BPP, Level 8: 0.161 -> 0.149 | Improved |
| add siblings' children context (ablation) | Ours entropy model · KITTI Odometry (ablation) | BPP, Level 12: 4.133 -> 3.878 | Improved |
| add ancestor context (ablation) | Ours entropy model · KITTI Odometry (ablation) | BPP, Level 8: 0.150 -> 0.149 | Improved |
| add ancestor context (ablation) | Ours entropy model · KITTI Odometry (ablation) | BPP, Level 12: 3.956 -> 3.878 | Improved |
| add surface priors (ablation) | Ours entropy model · KITTI Odometry (ablation) | BPP, Level 8: 0.151 -> 0.149 | Improved |
| add surface priors (ablation) | Ours entropy model · KITTI Odometry (ablation) | BPP, Level 12: 3.953 -> 3.878 | Improved |
| add siblings' children context (ablation) | Ours entropy model · KITTI Odometry (ablation) | BPP, Level 10: 1.071 -> 0.999 | Improved |
| full method vs VoxelContext, same octree level | VoxelContext · KITTI Odometry (no refinement) | BPP, Level 12: 4.371 -> 3.878 | Improved |
| full method vs VoxelContext, same octree level | VoxelContext · nuScenes (no refinement) | BPP, Level 12: 3.960 -> 3.487 | Improved |
| full method vs VoxelContext, same octree level | VoxelContext · KITTI Odometry (no refinement) | BPP, Level 8: 0.173 -> 0.149 | Improved |
Closest papers by meaning
- VoxelContext-Net: An Octree Based Framework for Point Cloud Compression (CVPR 2021 · similarity 0.93)
- OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression (AAAI 2022 · similarity 0.93)
- OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression (CVPR 2020 · similarity 0.92)
- TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression (CVPR 2025 · similarity 0.90)
- UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach (AAAI 2025 · similarity 0.88)
- SCP: Spherical-Coordinate-Based Learned Point Cloud Compression (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
