Research map / 3D vision / Human pose estimation
PoserNet: Refining Relative Camera Poses Exploiting Object Detections
Matteo Taiana, Matteo Toso, Stuart James, Alessio Del Bue
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 PoserNet refinement (ablation) | BB-initialised relative poses · 7-Scenes small graphs | median orientation error: 96.48 -> 20.39 | Improved |
| add PoserNet refinement (ablation) | KP-initialised relative poses · 7-Scenes small graphs | median orientation error: 36.26 -> 7.31 | Improved |
| add PoserNet refinement (ablation) | BB-initialised relative poses · 7-Scenes small graphs | median translation direction error: 89.30 -> 46.60 | Improved |
| add PoserNet refinement (ablation) | KP-initialised relative poses · 7-Scenes small graphs | median translation direction error: 87.23 -> 14.54 | Improved |
| add PoserNet refinement before motion averaging (ablation) | EIG-SE3 (BB init) · 7-Scenes | median orientation error: 78.46 -> 15.80 | Improved |
| add PoserNet refinement before motion averaging (ablation) | EIG-SE3 (KP init) · 7-Scenes | median orientation error: 25.37 -> 5.10 | Improved |
| add PoserNet refinement before motion averaging (ablation) | EIG-SE3 (BB init) · 7-Scenes | median translation error (m): 0.65 -> 0.52 | Improved |
| add PoserNet refinement before motion averaging (ablation) | EIG-SE3 (KP init) · 7-Scenes | median translation error (m): 0.61 -> 0.32 | Improved |
| add PoserNet refinement before motion averaging (ablation) | MultiReg (BB init) · 7-Scenes | median orientation error: 31.37 -> 35.60 | Hurt |
| add PoserNet refinement before motion averaging (ablation) | MultiReg (KP init) · 7-Scenes | median orientation error: 15.69 -> 35.73 | Hurt |
| add PoserNet refinement before motion averaging (ablation) | MultiReg (KP init) · 7-Scenes | median translation error (m): 0.64 -> 0.91 | Hurt |
| train PoserNet on small graphs instead of large graphs (ablation) | PoserNet · 7-Scenes large test graphs | median orientation error: 12.11 -> 6.85 | Improved |
Closest papers by meaning
- Pose without Guesses: Generalizable Object Pose Estimation From a Single Reference (IJCV 2026 · similarity 0.87)
- GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement (CVPR 2024 · similarity 0.86)
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · similarity 0.85)
- RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects (CVPR 2025 · similarity 0.85)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.84)
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.84)
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.
