Research map / Point clouds / Point cloud classification
Superpoint Network for Point Cloud Oversegmentation
Le Hui, Jia Yuan, Mingmei Cheng, Jin Xie, Xiaoya Zhang, Jian Yang
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 feature-space weights to coordinate-only association (ablation) | SPNet · S3DIS Area 5 | boundary recall: 78.35 -> 82.11 | Improved |
| add feature-space weights to coordinate-only association (ablation) | SPNet · S3DIS Area 5 | boundary precision: 9.43 -> 13.14 | Improved |
| add feature-space weights to coordinate-only association (ablation) | SPNet · S3DIS Area 5 | oracle overall accuracy: 95.10 -> 96.50 | Improved |
| add coordinate-space weights to feature-only association (ablation) | SPNet · S3DIS Area 5 | boundary recall: 82.03 -> 82.11 | No clear effect |
| add coordinate-space weights to feature-only association (ablation) | SPNet · S3DIS Area 5 | boundary precision: 12.01 -> 13.14 | Improved |
| vary k (nearest superpoints) beyond k=1 (ablation) | SPNet · S3DIS Area 5 | boundary recall | No clear effect |
| vary lambda (compactness) and iterations v (ablation) | SPNet · S3DIS Area 5 | boundary recall | No clear effect |
| use SPNet superpoints instead of SSP superpoints for segmentation | superpoint-based segmentation · vKITTI 6-fold | mIoU: 52.0 -> 57.0 | Improved |
| use SPNet superpoints instead of SSP superpoints for segmentation | superpoint-based segmentation · S3DIS 6-fold | mIoU: 68.4 -> 68.7 | Improved |
| use SPNet superpoints instead of SSP superpoints for segmentation | superpoint-based segmentation · S3DIS 6-fold | inference time (s): 9581 -> 2828 | Improved |
| end-to-end SPNet instead of SSP with graph-cut post-processing | superpoint generation · S3DIS Area 5 | inference time (s): 2327 -> 646 | Improved |
| use label consistency loss (SPNet vs SSP) | superpoint generation · vKITTI 6-fold (w/ RGB) | boundary recall: 90.37 -> 94.15 | Improved |
Closest papers by meaning
- Point Cloud Oversegmentation With Graph-Structured Deep Metric Learning (CVPR 2019 · similarity 0.92)
- Serialization based Point Cloud Oversegmentation (ICCV 2025 · similarity 0.91)
- Efficient LiDAR Point Cloud Oversegmentation Network (ICCV 2023 · similarity 0.91)
- Large-Scale Point Cloud Semantic Segmentation With Superpoint Graphs (CVPR 2018 · similarity 0.90)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (CVPR 2024 · similarity 0.87)
- LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds (CVPR 2025 · similarity 0.87)
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.
