Research map / Point clouds / Segmentation and detection
Instance Segmentation in 3D Scenes Using Semantic Superpoint Tree Networks
Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia
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 |
|---|---|---|---|
| build SST from instance centers rather than superpoint features (ablation) | SSTNet · ScanNet v2 val | mAP: 40.1 -> 47.3 | Improved |
| build SST from semantic scores rather than superpoint features (ablation) | SSTNet · ScanNet v2 val | mAP: 40.1 -> 43.5 | Improved |
| use semantic score plus instance center instead of all three features (ablation) | SSTNet · ScanNet v2 val | mAP: 48.9 -> 49.4 | Improved |
| add superpoint feature to score and center for SST construction (ablation) | SSTNet · ScanNet v2 val | mAP: 49.4 -> 48.9 | Hurt |
| learn node-splitting classifier instead of thresholding distance (ablation) | SST traversal · ScanNet v2 val | mAP: 46.3 -> 49.4 | Improved |
| learn node-splitting classifier instead of thresholding distance (ablation) | SST traversal · ScanNet v2 val | AP@25: 74.7 -> 74.0 | Hurt |
| use semantic superpoint tree instead of kNN superpoint graph (ablation) | SSTNet · ScanNet v2 val | mAP: 44.4 -> 49.4 | Improved |
| add CliqueNet refinement (ablation) | SSTNet · ScanNet v2 val | mAP: 49.4 -> 50.0 | Improved |
| add CliqueNet refinement (ablation) | SSTNet · ScanNet v2 val | AP@50: 64.3 -> 64.7 | Improved |
| add CliqueNet refinement (ablation) | SSTNet · ScanNet v2 val | AP@25: 74.0 -> 73.9 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PointGroup — PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation (CVPR 2020) · better on 3 of 3 shared results
- 3D-MPA — 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation (CVPR 2020) · 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
- Learning Superpoint Graph Cut for 3D Instance Segmentation (NeurIPS 2022 · similarity 0.90)
- SAM-guided Graph Cut for 3D Instance Segmentation (ECCV 2024 · similarity 0.90)
- SAI3D: Segment Any Instance in 3D Scenes (CVPR 2024 · similarity 0.89)
- Relation3D : Enhancing Relation Modeling for Point Cloud Instance Segmentation (CVPR 2025 · similarity 0.89)
- Semantic-aware SAM for Point-Prompted Instance Segmentation (CVPR 2024 · similarity 0.89)
- Insightful Instance Features for 3D Instance Segmentation (CVPR 2025 · similarity 0.88)
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.
