Research map / 3D vision / Human pose estimation
Real-Time Seamless Single Shot 6D Object Pose Prediction
Read the paperCheck 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 |
|---|---|---|---|
| Predict projected 3D bounding-box control points in one shot, then recover pose with PnP instead of using a multi-stage pipeline | 6D object pose estimation · LineMod | 2D reprojection accuracy: 83.9 -> 90.37 | Helped |
| Predict projected 3D bounding-box control points in one shot, then recover pose with PnP instead of using a multi-stage pipeline | 6D object pose estimation · LineMod | ADD accuracy: 43.6 -> 55.95 | Helped |
| Predict object pose jointly with object detection and identity, without assuming ground-truth image crops | 6D object pose estimation · Occlusion | MAP: 0.38 -> 0.48; 0.51 | Mixed |
| Use confidence-weighted averaging of predictions from neighboring grid cells (ablation) | Ours · LineMod | 2D projection accuracy: 1--2% | Helped |
| Remove the original image background and composite the object onto a random background (ablation) | Ours · LineMod | 2D projection accuracy: about 1% | Hurt |
| Increase input resolution from 544 × 544 to 688 × 688 (ablation) | Ours · LineMod | 2D projection accuracy: 90.37 -> 90.65 | Helped |
| Increase input resolution from 544 × 544 to 688 × 688 (ablation) | Ours · LineMod | speed: 50 fps -> 43 fps | Hurt |
Closest papers by meaning
- Single-Stage 6D Object Pose Estimation (CVPR 2020 · similarity 0.90)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.89)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.88)
- Open-Vocabulary Object 6D Pose Estimation (CVPR 2024 · similarity 0.88)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.87)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.87)
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.