Research map / 3D vision / 3D generation
TO-Scene: A Large-Scale Dataset for Understanding 3D Tabletop Scenes
Mutian Xu, Pei Chen, Haolin Liu, Xiaoguang Han
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 FV and DS tabletop-aware learning | Point Transformer · TO-Scene TO_Vanilla segmentation | mIoU: 77.08 -> 79.91 | Improved |
| add FV and DS tabletop-aware learning | Point Transformer · TO-Scene TO_ScanNet segmentation | mIoU: 67.17 -> 69.59 | Improved |
| add FV and DS tabletop-aware learning | PointNet++ · TO-Scene TO_ScanNet segmentation | mIoU: 53.97 -> 58.80 | Improved |
| add feature vector (FV) of tabletop-object discriminator (ablation) | Point Transformer · TO-Scene TO_Crowd segmentation | mIoU: 72.95 -> 75.06 | Improved |
| add dynamic sampling (DS) (ablation) | Point Transformer · TO-Scene TO_ScanNet segmentation | mIoU: 67.17 -> 68.34 | Improved |
| add FV and DS tabletop-aware learning | VoteNet · TO-Scene TO_ScanNet detection | mAP@0.25: 43.70 -> 56.93 | Improved |
| add FV and DS tabletop-aware learning | VoteNet · TO-Scene TO_Crowd detection | mAP@0.25: 48.27 -> 58.87 | Improved |
| add dynamic sampling (DS) (ablation) | VoteNet · TO-Scene TO_Crowd detection | mAP@0.25: 48.27 -> 58.05 | Improved |
| add FV and DS tabletop-aware learning | Group-Free 3D · TO-Scene TO_Vanilla detection | mAP@0.25: 61.75 -> 62.41 | Improved |
| add FV and DS tabletop-aware learning | Group-Free 3D · TO-Scene TO_ScanNet detection | mAP@0.25: 49.04 -> 57.57 | Improved |
| add feature vector (FV) (ablation) | Group-Free 3D · TO-Scene TO_Crowd detection | mAP@0.25: 59.61 -> 59.63 | No clear effect |
| use dynamic sampling instead of random sampling (ablation) | Point Transformer · TO_ScanNet segmentation | mIoU: +1.17% | Improved |
Closest papers by meaning
- MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning (NeurIPS 2025 · similarity 0.87)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.86)
- Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes (NeurIPS 2025 · similarity 0.85)
- MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations (NeurIPS 2024 · similarity 0.85)
- 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition (NeurIPS 2024 · similarity 0.85)
- OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations (NeurIPS 2025 · similarity 0.85)
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.
