Research map / 3D vision / Human pose estimation
SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation
Kai Chen, Qi Dou
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 vanilla transformer prior adaptation (ablation) | SGPA baseline · CAMERA25 | IoU75 mAP: 85.6 -> 87.8 | Improved |
| add vanilla transformer prior adaptation (ablation) | SGPA baseline · CAMERA25 | 5°2cm mAP: 61.5 -> 68.2 | Improved |
| add vanilla transformer prior adaptation (ablation) | SGPA baseline · REAL275 | IoU75 mAP: 59.2 -> 59.9 | Improved |
| add vanilla transformer prior adaptation (ablation) | SGPA baseline · REAL275 | 5°2cm mAP: 23.8 -> 33.3 | Improved |
| replace vanilla transformer with structure regularized low-rank transformer (ablation) | SGPA · REAL275 | 5°2cm mAP: 33.3 -> 35.9 | Improved |
| replace vanilla transformer with structure regularized low-rank transformer (ablation) | SGPA · CAMERA25 | 5°2cm mAP: 68.2 -> 70.7 | Improved |
| use random instance as prior instead of learned embedding prior (ablation) | SGPA · REAL275 | 5°2cm mAP: 35.9 -> 33.9 | Hurt |
| use random instance as prior instead of learned embedding prior (ablation) | SGPA · CAMERA25 | 5°2cm mAP: 70.7 -> 69.5 | No clear effect |
| reduce low-rank dimension n from 256 to 16 (ablation) | SGPA · REAL275 | 5°2cm mAP: 35.9 -> 27.7 | Hurt |
| use full rank 1024 instead of n=256 (ablation) | SGPA · REAL275 | 5°2cm mAP: 35.9 -> 33.3 | Hurt |
| vary low-rank dimension n from 16 to 1024 (ablation) | SGPA · CAMERA25 | 5°2cm mAP: 68.2 -> 70.7 | No clear effect |
| use SGPA prior adaptation instead of SPD | SPD · REAL275 | 5°2cm mAP: 19.3 -> 35.9 | Improved |
Later papers that compared with this method
9 later accepted papers report SGPA as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- CRISP: Object Pose and Shape Estimation with Test-Time Adaptation (CVPR 2025 · better on 1 of 2 shared results)
- Vision Foundation Model Enables Generalizable Object Pose Estimation (NeurIPS 2024 · better on 1 of 3 shared results)
- Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking (ECCV 2024 · better on 2 of 2 shared results)
- Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation (ICCV 2023 · better on 1 of 1 shared result)
- RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation (ECCV 2022 · better on 9 of 11 shared results)
- CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement (ECCV 2022 · better on 3 of 3 shared results)
- Category-Level 6D Object Pose and Size Estimation Using Self-Supervised Deep Prior Deformation Networks (ECCV 2022 · better on 3 of 3 shared results)
- GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-Wise Voting (CVPR 2022 · better on 1 of 2 shared results)
1 more not listed.
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
- Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation (CVPR 2024 · similarity 0.87)
- Vision Foundation Model Enables Generalizable Object Pose Estimation (NeurIPS 2024 · similarity 0.87)
- Structure-Aware Correspondence Learning for Relative Pose Estimation (CVPR 2025 · similarity 0.86)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.86)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.86)
- KPA-Tracker: Towards Robust and Real-Time Category-Level Articulated Object 6D Pose Tracking (AAAI 2024 · 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.
