Research map / 3D vision / Face and shape
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories
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 |
|---|---|---|---|
| Use OpenSeg instead of SGPN | Part instance segmentation · PartNet unseen categories, level 1 | part-category mAP (%): 55.7 -> 62.6 | Helped |
| Use OpenSeg instead of SGPN | Part instance segmentation · PartNet unseen categories, level 2 | part-category mAP (%): 29.7 -> 37.4 | Helped |
| Use OpenSeg instead of SGPN | Part instance segmentation · PartNet unseen categories, level 3 | part-category mAP (%): 29.5 -> 36.6 | Helped |
| Use OpenSeg instead of SGPN | Part instance segmentation · PartNet unseen categories, average across levels | part-category mAP (%): 46.8 -> 54.4 | Helped |
Closest papers by meaning
- Learning Fine-Grained Segmentation of 3D Shapes Without Part Labels (CVPR 2021 · similarity 0.90)
- PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data (ICLR 2026 · similarity 0.89)
- PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding (NeurIPS 2025 · similarity 0.88)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.87)
- 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition (NeurIPS 2024 · similarity 0.86)
- Activating Sparse Part Concepts for 3D Class Incremental Learning (CVPR 2025 · similarity 0.86)
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.