Research map / Point clouds / Segmentation and detection
SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 dynamic label propagation to graph embedding (ablation) | SSPC-Net · S3DIS Area5, supervision 0.002% | mIoU: 39.6 -> 40.9 | Helped |
| Add coupled attention to graph embedding and label propagation (ablation) | SSPC-Net · S3DIS Area5, supervision 0.002% | mIoU: 40.9 -> 43.0 | Helped |
| Add dynamic label propagation to graph embedding (ablation) | SSPC-Net · S3DIS Area5, supervision 0.01% | mIoU: 48.5 -> 50.0 | Helped |
| Add coupled attention to graph embedding and label propagation (ablation) | SSPC-Net · S3DIS Area5, supervision 0.01% | mIoU: 50.0 -> 51.5 | Helped |
| Increase supervision rate from 0.002% to 0.01%, 0.1%, and 1.0% | SSPC-Net · S3DIS Area5 | mIoU: 43.0; 51.5; 56.2; 58.3 | Helped |
| Change label propagation interval M among 20, 30, 40, 50, and 60 epochs (ablation) | SSPC-Net · S3DIS Area5, supervision 0.01% | mIoU: 50.2; 50.8; 51.5; 49.6; 49.9 | Mixed |
| Use SSPC-Net with 1pt supervision instead of Semi-Seg with 1pt supervision | S3DIS Fold 5 · S3DIS Fold 5 | mIoU: 44.5 -> 53.8 | Helped |
| Use SSPC-Net rather than the label-propagation- and coupled-attention-free baseline | S3DIS Fold 5, supervision 0.002% · S3DIS Fold 5 | mIoU: 39.6 -> 43.0 | Helped |
| Increase supervision from 0.01% to 0.05% | SSPC-Net · ScanNet test | mIoU: 27.1 -> 39.3 | Helped |
| Increase supervision from 0.01% to 0.05% | SSPC-Net · vKITTI 6-fold cross validation | mIoU: 41.0 -> 50.6 | Helped |
Closest papers by meaning
- Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds (CVPR 2020 · similarity 0.91)
- Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation (AAAI 2024 · similarity 0.90)
- LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds (CVPR 2025 · similarity 0.90)
- Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle (CVPR 2024 · similarity 0.90)
- Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling (CVPR 2024 · similarity 0.88)
- Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation (AAAI 2024 · 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.