Research map / 3D vision / Human pose estimation
Reconstruct Locally, Localize Globally: A Model Free Method for Object Pose Estimation
Ming Cai, Ian Reid
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 multi-view landmark alignment loss to reprojection loss (ablation) | RLLG object-coordinate head · Expo test set | 5cm5deg: 14.3 -> 39.3 | Improved |
| Add multi-view landmark alignment loss to reprojection loss (ablation) | RLLG object-coordinate head · Expo test set | ADD-10: 23.6 -> 52.5 | Improved |
| Add photometric loss to reprojection loss (ablation) | RLLG object-coordinate head · Expo test set | 5cm5deg: 14.3 -> 40.1 | Improved |
| Add photometric loss to reprojection loss (ablation) | RLLG object-coordinate head · Expo test set | ADD-10: 23.6 -> 51.3 | Improved |
| Add landmark alignment and photometric losses to reprojection loss (ablation) | RLLG object-coordinate head · Expo test set | 5cm5deg: 14.3 -> 53.1 | Improved |
| Add landmark alignment and photometric losses to reprojection loss (ablation) | RLLG object-coordinate head · Expo test set | ADD-10: 23.6 -> 58.5 | Improved |
| Use reprojection loss alone instead of direct depth supervision (ablation) | RLLG object-coordinate head · Expo test set | 5cm5deg: 61.3 -> 14.3 | Hurt |
| Use reprojection loss alone instead of direct depth supervision (ablation) | RLLG object-coordinate head · Expo test set | ADD-10: 57.1 -> 23.6 | Hurt |
| Use the model-free RLLG method instead of Dense-Fusion | LINEMOD · LINEMOD | ADD-10: 94 -> 82.88 | Hurt |
| Use the model-free RLLG method instead of PVNet | Occlusion LINEMOD · Occlusion LINEMOD | ADD-10: 40.8 -> 30.3 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.
- Dense-Fusion — DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (CVPR 2019) · better on 0 of 1 shared result
- PVNet — PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (CVPR 2019) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.89)
- iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 2024 · similarity 0.88)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.88)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.88)
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · 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.
