Research map / 3D vision / Human pose estimation
Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers
Tzu-Yuan Lin, Ho Lee, Kevin Doherty, Yonghyeon Lee, Sangbae Kim
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 multi-hypothesis registration (ablation) | Point2Pose · HO3D | ADD AUC: 65.52 -> 82.76 | Improved |
| add multi-hypothesis registration (ablation) | Point2Pose · HO3D | ADD-S AUC: 89.81 -> 95.07 | Improved |
| add SDF refinement (ablation) | Point2Pose · HO3D | ADD AUC: 77.37 -> 82.76 | Improved |
| add graph optimization (ablation) | Point2Pose · HO3D | ADD AUC: 78.80 -> 82.76 | Improved |
| use proposed keypoint sampling instead of SuperPoint only (ablation) | Point2Pose · HO3D | ADD AUC: 77.61 -> 82.76 | Improved |
| use proposed keypoint sampling instead of uniform sampling (ablation) | Point2Pose · HO3D | ADD AUC: 72.31 -> 82.76 | Improved |
| use long-range point tracking instead of short horizon (discard after 10 invisible frames) (ablation) | Point2Pose · YCBMultiTrack-Real mustard | ADD-S AUC: 38.52 -> 93.79 | Improved |
| use Point2Pose instead of BundleSDF | Point2Pose · YCBMultiTrack-Real | ADD-S AUC: 62.08 -> 89.43 | Improved |
| use Point2Pose instead of BundleSDF | Point2Pose · HO3D | ADD AUC: 87.36 -> 80.79 | Hurt |
| use Point2Pose instead of BundleSDF | Point2Pose · YCBInEOAT | ADD-S AUC: 94.51 -> 92.67 | Hurt |
Closest papers by meaning
- Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences (CVPR 2021 · similarity 0.88)
- ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation (NeurIPS 2026 · similarity 0.88)
- Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera (AAAI 2025 · similarity 0.86)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.86)
- ComPose: When to Trust Hands for Object Pose Tracking (NeurIPS 2026 · similarity 0.86)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (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.
