Research map / 3D vision / Human pose estimation
Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd
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 |
|---|---|---|---|
| Use the proposed Hough Forest framework with learned patch features | 6D object pose estimation · Cited multi-object dataset, average | F1 score: 0.633 -> 0.803 | Helped |
| Use the proposed Hough Forest framework with learned patch features | 6D object pose estimation · Cited single-object dataset, average | accuracy (%): 88.2 -> 89.1 | Helped |
| Add joint registration and hypotheses verification (ablation) | Our method · Supermarket objects, amita | score: 64.3 -> 71.2 | Helped |
| Add joint registration and hypotheses verification (ablation) | Our method · Bin picking, coffeecup | score: 33.5 -> 36.1 | Helped |
| Use deeper Sparse Autoencoder features rather than shallower ones (ablation) | Hough Forest patch features · Validation set on the authors’ dataset | F1-score | Helped |
| Increase the number of Sparse Autoencoder features (ablation) | Hough Forest patch features · Validation set on the authors’ dataset | F1-score | Helped |
| Increase patch size (ablation) | Hough Forest patch extraction · Validation set on the authors’ dataset | F1-score | Helped |
| Increase patch resolution (ablation) | Hough Forest patch extraction · Validation set on the authors’ dataset | F1-score | Helped |
| Reduce patch extraction stride (ablation) | Hough Forest patch extraction · Validation set on the authors’ dataset | F1-score | Helped |
| Pre-train each Sparse Autoencoder layer (ablation) | Sparse Autoencoder feature learning · Validation set on the authors’ dataset | F1-score | No clear effect |
| Add occlusion refinement to next-best-view entropy estimation (ablation) | Next-best-view selection · Crowded scenes and row-arranged object scenes | pose estimation accuracy | Helped |
Closest papers by meaning
- Open-Vocabulary Object 6D Pose Estimation (CVPR 2024 · similarity 0.86)
- iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting (CVPR 2025 · similarity 0.86)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.86)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.86)
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 2024 · similarity 0.86)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 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.