Research map / 3D vision / Human pose estimation
RPE-PAD: Relative Pose Estimation for Pose-agnostic Anomaly Detection
Zhipeng Zhang, Mengzan Qi, Rongkang Ma, Yingying Fang, Guixu Zhang, Tieyong Zeng, Zhi Li
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 Random View Synthesis Scheme (RVSS) (ablation) | RPE-PAD baseline · MAD | AUROC_I: 62.5 -> 77.8 | Improved |
| add IRPRN on top of RVSS (ablation) | RPE-PAD · MAD | AUROC_I: 77.8 -> 87.3 | Improved |
| add MPTS on top of RVSS (ablation) | RPE-PAD · MAD | AUROC_I: 77.8 -> 89.4 | Improved |
| add MPTS and IRPRN together (full vs RVSS+IRPRN) (ablation) | RPE-PAD · MAD | AUROC_I: 87.3 -> 93.8 | Improved |
| query-independent relative pose estimation instead of per-query optimization, with parameters fixed | OmniposeAD/SplatPose vs RPE-PAD · MAD (fixed parameters) | AUROC_I: 60.9 -> 93.8 | Improved |
| replace query-specific pose estimation with RPE-PAD | SplatPose · MAD inference time | total time (s): 4.103 -> 0.011 | Improved |
| RPE-PAD vs SplatPose on standard MAD detection | RPE-PAD · MAD | AUROC_I: 93.9 -> 93.8 | No clear effect |
| RPE-PAD vs baselines on real-world RAD | RPE-PAD · RAD | AUROC_I: 56.7 -> 77.8 | Improved |
Closest papers by meaning
- PIAD: Pose and Illumination agnostic Anomaly Detection (CVPR 2025 · similarity 0.88)
- Map-Relative Pose Regression for Visual Re-Localization (CVPR 2024 · similarity 0.85)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.85)
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · similarity 0.84)
- One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection (NeurIPS 2024 · similarity 0.84)
- Scene-agnostic Pose Regression for Visual Localization (CVPR 2025 · 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.
