Research map / Point clouds / Segmentation and detection
Few-Shot 3D Point Cloud Semantic Segmentation
Check 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 |
|---|---|---|---|
| Use attention-aware multi-prototype transductive inference instead of AttProtoNet | Few-shot point cloud semantic segmentation · S3DIS and ScanNet, 2-way/3-way 1-shot/5-shot | mean-IoU (%) | Helped |
| Use attention-aware multi-prototype transductive inference instead of AttProtoNet | Few-shot point cloud semantic segmentation · ScanNet 2-way 1-shot | mean-IoU (%): 36.33 -> 41.69 | Helped |
| Use geometric features only rather than all three feature levels (ablation) | Attention-aware multi-prototype transductive inference · S3DIS S0, 2-way 1-shot | mean-IoU (%): 53.77 -> 40.31 | Hurt |
| Use geometric features only rather than all three feature levels (ablation) | Attention-aware multi-prototype transductive inference · ScanNet S1, 2-way 1-shot | mean-IoU (%): 40.83 -> 26.91 | Hurt |
| Use semantic features only rather than all three feature levels (ablation) | Attention-aware multi-prototype transductive inference · S3DIS S0, 2-way 1-shot | mean-IoU (%): 53.77 -> 44.43 | Hurt |
| Use semantic features only rather than all three feature levels (ablation) | Attention-aware multi-prototype transductive inference · ScanNet S1, 2-way 1-shot | mean-IoU (%): 40.83 -> 34.51 | Hurt |
| Use metric-adaptive features only rather than all three feature levels (ablation) | Attention-aware multi-prototype transductive inference · S3DIS S0, 2-way 1-shot | mean-IoU (%): 53.77 -> 48.24 | Hurt |
| Use metric-adaptive features only rather than all three feature levels (ablation) | Attention-aware multi-prototype transductive inference · ScanNet S1, 2-way 1-shot | mean-IoU (%): 40.83 -> 35.07 | Hurt |
| Add metric-adaptive features to geometric and semantic features (ablation) | Attention-aware multi-prototype transductive inference · S3DIS S0, 2-way 1-shot | mean-IoU (%): 47.82 -> 53.77 | Helped |
| Add metric-adaptive features to geometric and semantic features (ablation) | Attention-aware multi-prototype transductive inference · ScanNet S1, 2-way 1-shot | mean-IoU (%): 38.69 -> 40.83 | Helped |
| Add semantic features to geometric and metric-adaptive features (ablation) | Attention-aware multi-prototype transductive inference · S3DIS S0, 2-way 1-shot | mean-IoU (%): 52.21 -> 53.77 | Helped |
| Add semantic features to geometric and metric-adaptive features (ablation) | Attention-aware multi-prototype transductive inference · ScanNet S1, 2-way 1-shot | mean-IoU (%): 36.12 -> 40.83 | Helped |
Closest papers by meaning
- Rethinking Few-shot 3D Point Cloud Semantic Segmentation (CVPR 2024 · similarity 0.92)
- Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation (ICLR 2025 · similarity 0.89)
- Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation (AAAI 2025 · similarity 0.89)
- Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation (AAAI 2024 · similarity 0.89)
- Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model (CVPR 2025 · similarity 0.89)
- DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation (ICML 2025 · similarity 0.89)
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.