Research map / 3D vision / Human pose estimation
Polarimetric Pose Prediction
Daoyi Gao, Yitong Li, Patrick Ruhkamp, Iuliia Skobleva, Magdalena Wysocki, HyunJun Jung, Pengyuan Wang, Arturo Guridi, Benjamin Busam
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 |
|---|---|---|---|
| use polarised RGB input instead of unpolarised RGB (ablation) | PPP-Net · Fork | ADD: 85.4 -> 86.1 | Improved |
| use polarised RGB input instead of unpolarised RGB (ablation) | PPP-Net · Cup | ADD: 91.1 -> 91.3 | No clear effect |
| add normals output head (ablation) | PPP-Net · Fork | ADD: 86.1 -> 92.9 | Improved |
| add physical normals as separate input (ablation) | PPP-Net · Fork | ADD: 92.9 -> 95.9 | Improved |
| add physical normals as separate input (ablation) | PPP-Net · Cup | ADD: 91.3 -> 97.2 | Improved |
| add physical normals input (normals error) (ablation) | PPP-Net · Fork | normal mean error: 11.0 -> 6.5 | Improved |
| add NOCS output before Patch-PnP (ablation) | PPP-Net · Fork | ADD: 79.3 -> 95.9 | Improved |
| add NOCS output before Patch-PnP (ablation) | PPP-Net · Teapot | ADD: 72.7 -> 99.9 | Improved |
| encode physical normals with a dedicated encoder instead of concatenation (ablation) | PPP-Net · Fork | ADD: 87.6 -> 95.9 | Improved |
| encode physical normals with a dedicated encoder instead of concatenation (ablation) | PPP-Net · Knife | ADD: 86.1 -> 96.4 | Improved |
| predicted instead of GT bounding box at test (ablation) | PPP-Net · Cup | ADD: 99.0 -> 97.2 | Hurt |
| use incorrect refractive index (1.5) in training and testing (ablation) | PPP-Net · Knife | ADD: 96.4 -> 90.1 | Hurt |
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
- S$$^{2}$$P$$^{3}$$: Self-Supervised Polarimetric Pose Prediction (IJCV 2024 · similarity 0.90)
- Polarimetric Relative Pose Estimation (ICCV 2019 · similarity 0.88)
- Linear Differential Constraints for Photo-Polarimetric Height Estimation (ICCV 2017 · similarity 0.86)
- Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset (CVPR 2024 · similarity 0.85)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.85)
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 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.
