Research map / Point clouds / Point cloud classification
Sparse Tensor-Based Multiscale Representation for Point Cloud Geometry Compression
Jianqiang Wang, Dandan Ding, Zhu Li, Xiaoxing Feng, Chuntong Cao, Zhan Ma
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 SLNE to One-Stage SOPA (ablation) | One-Stage SOPA · 8iVFB lossless | bpp gain over G-PCC: +5.5% -> -25.1% | Improved |
| add SLNE to 3-Stage SOPA (ablation) | 3-Stage SOPA · 8iVFB lossless | bpp gain over G-PCC: -31.7% -> -35.3% | Improved |
| add SLNE to 8-Stage SOPA (ablation) | 8-Stage SOPA · 8iVFB lossless | bpp gain over G-PCC | No clear effect |
| increase SOPA stages from 1 to 3 (ablation) | One-Stage SOPA · 8iVFB lossless | bpp gain over G-PCC: +5.5% -> -31.7% | Improved |
| increase SOPA stages from 3 to 8 (ablation) | 3-Stage SOPA · 8iVFB lossless | bpp gain over G-PCC: -31.7% -> -38.5% | Improved |
| use fully autoregressive n-Stage instead of 8-Stage (ablation) | 8-Stage SOPA · 8iVFB lossless | bpp gain / decode time: -38.5% -> -39.3%; decoding 1.78 -> 2 hr | Mixed |
| reduce channels from C32 to C16 (k=3) (ablation) | 8-Stage SOPA · 8iVFB_vox10 lossless | bits per point: 0.633 -> 0.642; model size 4.89 MB -> 1.31 MB | No clear effect |
| enlarge kernel from k=3 to k=5 (C32) (ablation) | 8-Stage SOPA · 8iVFB_vox10 lossless | bits per point: 0.633 -> 0.655 | Hurt |
| enlarge kernel from k=3 to k=5 (C32) (ablation) | 8-Stage SOPA · KITTI_vox2cm lossless | bits per point: 6.880 -> 6.130 | Improved |
| increase channels from C16 to C32 (k=5) (ablation) | 8-Stage SOPA · KITTI_vox2cm lossless | bits per point: 6.334 -> 6.130 | Improved |
| increase channels from C16 to C32 (k=3) (ablation) | 8-Stage SOPA · KITTI_vox2cm lossless | bits per point: 7.021 -> 6.880 | Improved |
| sparse tensor multiscale SOPA vs octree OctAttention | SparsePCGC · 8iVFB lossless | bpp gain over G-PCC: -34.9% -> -44.2% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- OctAttention — OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression (AAAI 2022) · better on 2 of 2 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
- patchDPCC: A Patchwise Deep Compression Framework for Dynamic Point Clouds (AAAI 2024 · similarity 0.89)
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.87)
- TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression (CVPR 2025 · similarity 0.87)
- UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach (AAAI 2025 · similarity 0.87)
- RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds (CVPR 2025 · similarity 0.87)
- Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection (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.
