Research map / 3D vision / Human pose estimation
SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation
Yan Di, Fabian Manhardt, Gu Wang, Xiangyang Ji, Nassir Navab, Federico Tombari
Read the paperCheck 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 the cross-layer 3D consistency loss L_cl-3D (ablation) | SO-Pose · LM | ADD(-S) 0.02d: 41.6 -> 45.9 | Improved |
| add the cross-layer 3D consistency loss L_cl-3D (ablation) | SO-Pose · LM | 2deg2cm: 67.4 -> 76.9 | Improved |
| add the cross-layer 2D consistency loss L_cl-2D (ablation) | SO-Pose · LM | ADD(-S) 0.02d: 44.7 -> 45.9 | Improved |
| add the cross-layer 2D consistency loss L_cl-2D (ablation) | SO-Pose · LM | 2deg2cm: 73.1 -> 76.9 | Improved |
| add both cross-layer consistency losses (ablation) | SO-Pose · LM | ADD(-S) 0.02d: 36.6 -> 45.9 | Improved |
| add both cross-layer consistency losses (ablation) | SO-Pose · LM | 2deg2cm: 59.1 -> 76.9 | Improved |
| add both cross-layer consistency losses (ablation) | SO-Pose · LM | ADD(-S) 0.1d: 94.0 -> 96.0 | Improved |
| add the self-occlusion branch and L_cdpn to CDPN* | CDPN* · LM | ADD(-S): 92.82 -> 94.77 | Improved |
| add the consistency loss L_cdpn on top of the self-occlusion branch in CDPN* (ablation) | CDPN*-ours · LM | ADD(-S): 93.09 -> 94.77 | Improved |
| add the self-occlusion branch to CDPN* without L_cdpn (ablation) | CDPN* · LM | 5deg5cm: 97.03 -> 97.06 | No clear effect |
| use ResNeSt50 instead of ResNet34 backbone (ablation) | SO-Pose · YCB-V | ADD(-S): 54.6 -> 56.8 | Improved |
| use ResNeSt50 instead of ResNet34 backbone (ablation) | SO-Pose · YCB-V | AUC of ADD(-S): 82.3 -> 83.9 | Improved |
Later papers that compared with this method
5 later accepted papers report SO-Pose as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Environment-Agnostic Pose: Generating Environment-independent Object Representations for 6D Pose Estimation (ICCV 2025 · better on 1 of 1 shared result)
- CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network (ICCV 2023 · better on 3 of 4 shared results)
- Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation (ICCV 2023 · better on 1 of 1 shared result)
- DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation (CVPR 2022 · better on 1 of 1 shared result)
- ZebraPose: Coarse To Fine Surface Encoding for 6DoF Object Pose Estimation (CVPR 2022 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 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 7 of 7 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
- Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation (TPAMI 2021 · similarity 0.93)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.91)
- Self6D: Self-Supervised Monocular 6D Object Pose Estimation (ECCV 2020 · similarity 0.90)
- Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking (ECCV 2024 · similarity 0.90)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.89)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · 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.
