Research map / 3D vision / Human pose estimation
Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation
Nathaniel Merrill, Yuliang Guo, Xingxing Zuo, Xinyu Huang, Stefan Leutenegger, Xi Peng, Liu Ren, Guoquan Huang
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 projected 3D keypoint priors for symmetric-object tracking (ablation) | Object SLAM · T-LESS | e_vsd < 0.3 recall: 16.2 -> 63.7 | Improved |
| add projected 3D keypoint priors for symmetric-object tracking (ablation) | Object SLAM · YCB-Video | ADD-S AUC: 88.7 -> 90.3 | Improved |
| train predicted keypoint covariance with the MLE loss (ablation) | Keypoint network in Object SLAM · YCB-Video | ADD-S AUC: 47.0 -> 90.3 | Improved |
| use predicted covariance rather than a manually tuned residual weight (ablation) | Object SLAM · YCB-Video | ADD-S AUC: 59.1 -> 90.3 | Improved |
| use predicted covariance rather than a manually tuned residual weight (ablation) | Object SLAM · T-LESS | e_vsd < 0.3 recall: 13.8 -> 63.7 | Improved |
| use multi-view SLAM rather than single-view estimation (ablation) | Object pose estimation · YCB-Video | ADD-S AUC: 65.7 -> 90.3 | Improved |
| use multi-view SLAM rather than single-view estimation (ablation) | Object pose estimation · T-LESS | e_vsd < 0.3 recall: 48.1 -> 63.7 | Improved |
| train with synthetic data in addition to real data (ablation) | Object SLAM · T-LESS | e_vsd < 0.3 recall: 45.9 -> 63.7 | Improved |
| use dataset-provided camera poses instead of estimated camera poses (ablation) | Object SLAM · YCB-Video | ADD-S AUC: 90.3 -> 90.5 | No clear effect |
| use MLE-trained uncertainty estimates (ablation) | Keypoint network · Rendered YCB-Video keypoints | points passing 99% confidence chi-square test: 7.1% -> 91.0% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- GDR-Net — GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (CVPR 2021) · better on 1 of 2 shared results
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
- Object Pose Estimation With Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation (CVPR 2023 · similarity 0.89)
- Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation (ICCV 2023 · similarity 0.88)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.87)
- iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting (CVPR 2025 · similarity 0.86)
- Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation (CVPR 2024 · similarity 0.86)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 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.
