Research map / 3D vision / 3D generation
CoSMo3D: Open-World Promptable 3D Semantic Segmentation through LLM-Guided Canonical Spatial Modeling
Li Jin, Weikai Chen, Yujie Wang, Yingda Yin, Zeyu Hu, Runze Zhang, Keyang Luo, Shengju Qian, Xin Wang, Xueying Qin
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 hard-negative sampling (ablation) | CoSMo3D baseline (Find3D retrained) · 3DCompat canonical {Part} of {Obj.} | mIoU: 36.89 -> 38.30 | Improved |
| add canonical map anchoring loss (ablation) | CoSMo3D · 3DCompat canonical {Part} of {Obj.} | mIoU: 38.30 -> 41.71 | Improved |
| add cross-category canonicalization of training data (ablation) | CoSMo3D · 3DCompat canonical {Part} of {Obj.} | mIoU: 41.71 -> 43.34 | Improved |
| add canonical box calibration loss (ablation) | CoSMo3D · 3DCompat canonical {Part} of {Obj.} | mIoU: 43.34 -> 47.51 | Improved |
| add cross-category canonicalization (ablation) | CoSMo3D · 3DCompat rotated {Part} of {Obj.} | mIoU: 42.48 -> 42.63 | No clear effect |
| retrain Find3D on the curated canonical dataset | Find3D · 3DCompat-Coarse canonical {Part} | mIoU: 25.36 -> 45.00 | Improved |
| use CoSMo3D instead of retrained Find3D | Find3D · 3DCompat-Coarse | mIoU: 36.89 -> 47.51 | Improved |
| use CoSMo3D instead of Find3D on single-word prompts | Find3D · PartNet-E canonical | mIoU: PartSLIP++ 32.71 vs ours 17.19 | Mixed |
| rotate objects at test time | CoSMo3D · 3DCompat-Coarse {Part} of {Obj.} | mIoU: 47.51 -> 47.74 | No clear effect |
Closest papers by meaning
- One-shot 3D Object Canonicalization based on Geometric and Semantic Consistency (CVPR 2025 · similarity 0.90)
- Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes (NeurIPS 2025 · similarity 0.87)
- Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering (NeurIPS 2026 · similarity 0.87)
- COS3D: Collaborative Open-Vocabulary 3D Segmentation (NeurIPS 2025 · similarity 0.87)
- Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models (NeurIPS 2026 · similarity 0.86)
- Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space (AAAI 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.
