Research map / 3D vision / Human pose estimation
Uncertainty-Driven 6D Pose Estimation of Objects and Scenes From a Single RGB Image
Check 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 |
|---|---|---|---|
| add L1 regularization to intermediate auto-context outputs (ablation) | Auto-context regression forest · Texture-less object dataset [7], RGB, single object | 2D Projection: 73.7% vs. 38.0% | Helped |
| use L1 regularization instead of L2 regularization (ablation) | Auto-context regression forest · Texture-less object dataset [7], RGB, single object | 2D Projection: 68.6% to 73.7%; loss of 5.1% | Helped |
| add the auto-context framework (ablation) | Regression forest · Texture-less object dataset [7], RGB, single object | 2D Projection: 59.3% to 73.7%; +14.4% | Helped |
| add uncertainty-based pose refinement using object-coordinate distributions (ablation) | Pose estimation pipeline · Texture-less object dataset [7], RGB, single object | 2D Projection: 4.2% | Helped |
| add uncertainty-based pose refinement using object-coordinate distributions (ablation) | Pose estimation pipeline · Texture-less object dataset [7], RGB, single object | 6D Pose (Metric of [7]): 17.9% | Helped |
| use auto-context with regularization (ablation) | RGB-D pose estimation pipeline · Texture-less object dataset [7], RGB-D, single object | 6D Pose (5cm 5°): +2.4% | Helped |
| add label-guided sharing of a fixed RANSAC hypothesis budget across objects (ablation) | Multi-object pose estimation · Brachmann et al. [2] multi-object dataset, 13 objects | Average precision: 0.49 AP to 0.51 AP | Helped |
| add label-guided sharing of the hypothesis budget across unknown scenes (ablation) | Camera localization · 7 scenes dataset [23], RGB, scene unknown | 6D Pose (5cm 5°): 33.1% to 50.0% | Helped |
Closest papers by meaning
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.90)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.90)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.88)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.88)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.88)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.88)
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.