Research map / Point clouds / Shape and surface completion
Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D Shapes
Xiaogang Wang, Bin Zhou, Yahao Shi, Xiaowu Chen, Qinping Zhao, Kai Xu
Check 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 MON to jointly refine motion-part segmentation and motion attributes (ablation) | Shape2Motion · Shape2Motion benchmark | IoU: 82.3 -> 84.7 | Improved |
| add MON to jointly refine motion-part segmentation and motion attributes (ablation) | Shape2Motion · Shape2Motion benchmark | EPE: 0.028 -> 0.025 | Improved |
| add MON to jointly refine motion-part segmentation and motion attributes (ablation) | Shape2Motion · Shape2Motion benchmark | OE: 0.12 -> 0.11 | Improved |
| add MON to jointly refine motion-part segmentation and motion attributes (ablation) | Shape2Motion · Hu et al. dataset | IoU: 58.6 -> 64.7 | Improved |
| add MON to jointly refine motion-part segmentation and motion attributes (ablation) | Shape2Motion · Hu et al. dataset | EPE: 0.074 -> 0.061 | Improved |
| add MON to jointly refine motion-part segmentation and motion attributes (ablation) | Shape2Motion · Hu et al. dataset | MD: 0.028 -> 0.024 | Improved |
| add MON to jointly refine motion-part segmentation and motion attributes (ablation) | Shape2Motion · Hu et al. dataset | OE: 0.78 -> 0.12 | Improved |
| replace the motion attribute proposal module with direct attribute regression (ablation) | Shape2Motion · Shape2Motion benchmark | mobility proposal similarity | Hurt |
| use motion-driven proposal matching to pair motion parts with motion attributes | Shape2Motion · Shape2Motion benchmark | IoU: 79.4 -> 84.7 | Improved |
| use motion-driven proposal matching to pair motion parts with motion attributes | Shape2Motion · Shape2Motion benchmark | MD: 0.11 -> 0.01 | Improved |
| use motion-driven proposal matching to pair motion parts with motion attributes | Shape2Motion · Shape2Motion benchmark | OE: 3.13 -> 0.11 | Improved |
| use motion-driven proposal matching to pair motion parts with motion attributes | Shape2Motion · Shape2Motion benchmark | TA: 0.96 -> 0.98 | Improved |
Closest papers by meaning
- Semi-Weakly Supervised Object Kinematic Motion Prediction (CVPR 2023 · similarity 0.87)
- ODIN: A Single Model for 2D and 3D Segmentation (CVPR 2024 · similarity 0.85)
- Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos (CVPR 2025 · similarity 0.84)
- PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation (CVPR 2024 · similarity 0.84)
- Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking (CVPR 2024 · similarity 0.84)
- GMOS: Grounding Moving Object Segmentation in 3D Space and Time (NeurIPS 2026 · similarity 0.84)
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.
