Research map / 3D vision / Depth and stereo
Polarimetric Multi-View Inverse Rendering
Jinyu Zhao, Yusuke Monno, Masatoshi Okutomi
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 50% random azimuth ambiguity to AoP input (ablation) | Polarimetric MVIR · Synthetic average (perturbed AoP) | accuracy error (x10^-2): 0.6089 -> 0.6187 | Hurt |
| add 50% ambiguity and 24 deg Gaussian noise to AoP input (ablation) | Polarimetric MVIR · Synthetic average (perturbed AoP) | accuracy error (x10^-2): 0.6089 -> 0.7175 | Hurt |
| add 50% ambiguity and 24 deg Gaussian noise to AoP input (ablation) | Polarimetric MVIR · Synthetic average (perturbed AoP) | completeness error (x10^-2): 0.8630 -> 0.9643 | Hurt |
| raise AoP noise from 0 to 24 deg under 50% ambiguity (ablation) | Polarimetric MVIR · Synthetic average (perturbed AoP) | accuracy error (x10^-2): 0.6187 -> 0.7175 | Hurt |
| add 50% ambiguity only (ablation) | Polarimetric MVIR · Synthetic average (perturbed AoP) | completeness error (x10^-2): 0.8630 -> 0.8727 | Hurt |
| add 50% ambiguity and 12 deg noise (ablation) | Polarimetric MVIR · Synthetic average (perturbed AoP) | accuracy error (x10^-2): 0.6089 -> 0.6367 | Hurt |
| replace best existing MVS (CMPMVS) with Polarimetric MVIR under 50% ambiguity and 24 deg noise | CMPMVS · Synthetic average (perturbed AoP) | accuracy error (x10^-2): 0.8361 -> 0.7175 | Improved |
| add polarimetric cost and photometric refinement over MVIR | MVIR · Synthetic average | accuracy error (x10^-2): 0.8612 -> 0.6089 | Improved |
| add polarimetric cost and photometric refinement over MVIR | MVIR · Synthetic average | completeness error (x10^-2): 1.0909 -> 0.8630 | Improved |
Closest papers by meaning
- Polarimetric Multi-View Stereo (CVPR 2017 · similarity 0.92)
- Thermal Polarimetric Multi-view Stereo (ICCV 2025 · similarity 0.90)
- Glossy Object Reconstruction with Cost-effective Polarized Acquisition (CVPR 2025 · similarity 0.89)
- High-Fidelity Polarimetric Implicit 3D Reconstruction with View-Dependent Physical Representation (AAAI 2025 · similarity 0.89)
- NeISF: Neural Incident Stokes Field for Geometry and Material Estimation (CVPR 2024 · similarity 0.88)
- NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images (CVPR 2024 · similarity 0.87)
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.
