Research map / Point clouds / Point cloud classification
OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
Lila Huang, Shenlong Wang, Kelvin Wong, Jerry Liu, Raquel Urtasun
Check 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 |
|---|---|---|---|
| increase aggregation count from 0 to 4 (ablation) | OctSqueeze entropy model · NorthAmerica, Depths 12, 14, 16 | bitrate: 3.48 -> 3.17; 8.91 -> 8.32; 14.97 -> 14.33 | Improved |
| use 5 instead of 4 aggregations (ablation) | OctSqueeze entropy model · NorthAmerica, Depths 12, 14, 16 | bitrate: 3.17 -> 3.27; 8.32 -> 8.51; 14.33 -> 14.55 | Hurt |
| add parental context aggregation instead of copying each node's own context (ablation) | OctSqueeze entropy model, K=4 · NorthAmerica, Depths 12, 14, 16 | bitrate: 3.47 -> 3.17; 8.92 -> 8.32; 14.98 -> 14.33 | Improved |
| add parent occupancy feature to the level feature (ablation) | OctSqueeze entropy model, K=4 · NorthAmerica, Depth 12 | bitrate: 3.86 -> 3.44 | Improved |
| add octant index feature (ablation) | OctSqueeze entropy model, K=4 · NorthAmerica, Depth 12 | bitrate: 3.44 -> 3.34 | Improved |
| add spatial location feature (ablation) | OctSqueeze entropy model, K=4 · NorthAmerica, Depth 12 | bitrate: 3.34 -> 3.17 | Improved |
| use an octree-structured method rather than a dense voxel encoder | NorthAmerica LiDAR compression · NorthAmerica | point-to-plane PSNR: 33.76 -> 48.95 | Improved |
| use an octree-structured method rather than a dense voxel encoder | NorthAmerica LiDAR compression · NorthAmerica | bitrate: 26.81 -> 1.61 | Improved |
Later papers that compared with this method
1 later accepted paper reports OctSqueeze as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- VoxelContext-Net: An Octree Based Framework for Point Cloud Compression (CVPR 2021 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SCP: Spherical-Coordinate-Based Learned Point Cloud Compression (AAAI 2024 · similarity 0.87)
- msLPCC: A Multimodal-Driven Scalable Framework for Deep LiDAR Point Cloud Compression (AAAI 2024 · similarity 0.87)
- RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds (CVPR 2025 · similarity 0.87)
- Efficient LiDAR Reflectance Compression via Scanning Serialization (ICML 2025 · similarity 0.86)
- UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach (AAAI 2025 · similarity 0.85)
- TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression (CVPR 2025 · similarity 0.85)
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.
