Research map / 3D vision / Human pose estimation
StablePose: Learning 6D Object Poses From Geometrically Stable Patches
Yifei Shi, Junwen Huang, Xin Xu, Yifan Zhang, Kai Xu
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 |
|---|---|---|---|
| Use geometrically stable patch triplets rather than one-patch groups (ablation) | StablePose · T-LESS SISO | e_ADI recall: 0.70 -> 0.88 | Improved |
| Use geometrically stable patch triplets rather than two-patch groups (ablation) | StablePose · T-LESS SISO | e_ADI recall: 0.76 -> 0.88 | Improved |
| Use geometrically stable patch triplets rather than five-patch groups (ablation) | StablePose · T-LESS SISO | e_ADI recall: 0.73 -> 0.88 | Improved |
| Use stability-based rather than size-based patch-group sampling (ablation) | StablePose · T-LESS SISO | e_ADI recall: 0.85 -> 0.88 | Improved |
| Use stability-based rather than distance-based patch-group sampling (ablation) | StablePose · T-LESS SISO | e_ADI recall: 0.77 -> 0.88 | Improved |
| Add patch-wise pose estimation (ablation) | StablePose · T-LESS SISO | e_ADI recall: 0.73 -> 0.88 | Improved |
| Use back-propagate-with-all rather than baseline symmetry handling (ablation) | StablePose · T-LESS SISO | e_VSD recall: 0.54 -> 0.73 | Improved |
| Use StablePose instead of the strongest listed baseline | 6D pose estimation · T-LESS | e_ADI/e_VSD recall: 0.86 vs 0.76 (VIVO e_ADI); 0.88 vs 0.75 (SISO e_ADI); 0.69 vs 0.50 (VIVO e_VSD); 0.73 vs 0.64 (SISO e_VSD) | Improved |
| Use StablePose instead of CASS | category-level pose estimation · ShapeNetPose | 10°10cm: 13.9 -> 21.4 | Improved |
| Use depth-only StablePose instead of RGBD CosyPose | 6D pose estimation · LineMOD-O SISO | e_ADI/ADD recall: 0.68 -> 0.63 | Hurt |
Later papers that compared with this method
2 later accepted papers report StablePose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework (CVPR 2022 · better on 2 of 4 shared results)
- OVE6D: Object Viewpoint Encoding for Depth-Based 6D Object Pose Estimation (CVPR 2022 · better on 1 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
- GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator (TPAMI 2025 · similarity 0.89)
- DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency (ICCV 2021 · similarity 0.88)
- GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-Wise Voting (CVPR 2022 · similarity 0.88)
- Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation (ICCV 2023 · similarity 0.88)
- CosyPose: Consistent multi-view multi-object 6D pose estimation (ECCV 2020 · similarity 0.88)
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 2024 · 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.
