Research map / 3D vision / Human pose estimation
GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-Wise Voting
Yan Di, Ruida Zhang, Zhiqiang Lou, Fabian Manhardt, Xiangyang Ji, Nassir Navab, Federico Tombari
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 confidence-aware rotation prediction (ablation) | GPV-Pose · REAL275 | 3D_75: 52.0 to 56.9 | Improved |
| add confidence-aware rotation prediction (ablation) | GPV-Pose · REAL275 | 5°2cm: 19.9 to 22.7 | Improved |
| add symmetry-aware reconstruction to confidence-aware rotation (ablation) | GPV-Pose · REAL275 | 3D_75: 56.9 to 60.4 | Improved |
| add bounding-box pose consistency terms (ablation) | GPV-Pose · REAL275 | 3D_75: 60.4 to 63.2 | Improved |
| add bounding-box pose consistency terms (ablation) | GPV-Pose · REAL275 | 5°2cm: 25.3 to 29.9 | Improved |
| add point-cloud pose and size consistency (ablation) | GPV-Pose · REAL275 | 3D_75: 60.4 to 61.7 | Improved |
| train a single model across categories rather than one model per category | GPV-Pose · REAL275 | 5°5cm: 44.2 vs. 42.9 | Hurt |
| use GPV-Pose rather than the Ours(FS-Net) baseline | REAL275 · REAL275 | 3D_75: 52.0 -> 64.4 | Improved |
| use GPV-Pose rather than SGPA | REAL275 · REAL275 | 5°2cm: 32.0 vs. 35.9 | Hurt |
| apply GPV-Pose to instance-level pose estimation | LineMod · LineMod | ADD-(S): 98.2% for GPV-Pose compared to 98.2% for DualPoseNet | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 3 on most shared results.
- SGPA — SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation (ICCV 2021) · better on 1 of 2 shared results
- DualPoseNet — DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose Consistency (ICCV 2021) · better on 0 of 1 shared result
- PVN3D — PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (CVPR 2020) · 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
- GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.89)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.89)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · similarity 0.89)
- Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation (CVPR 2024 · similarity 0.89)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.89)
- GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement (CVPR 2024 · similarity 0.89)
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.
