Research map / Point clouds / Point cloud classification
OctFormer: Efficient Octree-Based Transformer for Point Cloud Compression with Local Enhancement
Mingyue Cui, Junhua Long, Mingjian Feng, Boyang Li, Huang Kai
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 |
|---|---|---|---|
| Increase the non-overlapped context window size from N=32 to N=1024 (ablation) | OctFormer · ScanNet, D=9 | Bpp: 6.416 -> 6.021 | Improved |
| Add OctLeFF in place of the vanilla feed-forward network (ablation) | OctFormer · ScanNet, D=9 | Bpp: 6.212 -> 6.144 | Improved |
| Add OctPEG instead of absolute positional encoding (ablation) | OctFormer · ScanNet, D=9 | Bpp: 6.212 -> 6.161 | Improved |
| Use absolute positional encoding (ablation) | OctFormer · ScanNet, D=9 | Bpp: 6.212 -> 6.213 | No clear effect |
| Add both OctLeFF and OctPEG (ablation) | OctFormer · ScanNet, D=9 | Bpp: 6.212 -> 6.135 | Improved |
| Use OctLeFF and OctPEG rather than APE alone (ablation) | OctFormer · ScanNet, D=9 | parameters: 5.66 M -> 4.28 M | Improved |
| Use OctFormer instead of OctAttention without sibling-occupancy features | OctAttention · SemanticKITTI, 1,000 dummy octree nodes | decode time (s): 2.060 -> 0.007 | Improved |
| Use OctFormer instead of VoxelContext-Net | VoxelContext-Net · SemanticKITTI, D=12 | Bpp: 4.497 -> 3.708 | Improved |
| Use OctFormer instead of VoxelContext-Net | VoxelContext-Net · SemanticKITTI, D=10 | Bpp: 0.951 -> 0.963 | Hurt |
| Use OctFormer instead of OctAttention | OctAttention · SemanticKITTI, D=12 | Bpp: 3.740 -> 3.708 | Improved |
Later papers that compared with this method
6 later accepted papers report OctFormer as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Rethinking Serialization in Linear 3D Vision: Decoupling Anisotropic Geometry from Isotropic Semantics (ICML 2026 · better on 1 of 1 shared result)
- R²D-LPCC: Relevance-Ranking Guided Region-Adaptive Dynamic LiDAR Point Cloud Compression (AAAI 2026 · better on 1 of 1 shared result)
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation (CVPR 2024 · better on 2 of 3 shared results)
- Point Transformer V3: Simpler Faster Stronger (CVPR 2024 · better on 2 of 2 shared results)
- SegPoint: Segment Any Point Cloud via Large Language Model (ECCV 2024 · better on 1 of 2 shared results)
- KPConvX: Modernizing Kernel Point Convolution with Kernel Attention (CVPR 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- OctAttention — OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression (AAAI 2022) · better on 1 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
- OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression (AAAI 2022 · similarity 0.91)
- Point Cloud Compression with Sibling Context and Surface Priors (ECCV 2022 · similarity 0.91)
- VoxelContext-Net: An Octree Based Framework for Point Cloud Compression (CVPR 2021 · similarity 0.90)
- TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression (CVPR 2025 · similarity 0.89)
- UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach (AAAI 2025 · similarity 0.86)
- Point Transformer V3: Simpler Faster Stronger (CVPR 2024 · 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.
