Research map / 3D vision / Depth and stereo
Deep Shape from Polarization
Yunhao Ba, Alex Gilbert, Franklin Wang, Jinfa Yang, Rui Chen, Yiqin Wang, Lei Yan, Boxin Shi, Achuta Kadambi
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 polarization images with physics priors instead of an unpolarized image (ablation) | shape-from-shading style network · Deep SfP dataset (example scene) | mean angular error (degrees): 28.63 -> 19.46 | Improved |
| add ambiguous physics-based normal maps as network input (ablation) | CNN on polarization images only · Deep SfP dataset | mean angular error (degrees) | Improved |
| replace physics-only SfP with physics-based deep learning | Smith et al. · Deep SfP test set, whole set | mean angular error (degrees): 41.44 -> 18.52 | Improved |
| replace physics-only SfP with physics-based deep learning | Mahmoud et al. · Deep SfP test set, whole set | mean angular error (degrees): 49.03 -> 18.52 | Improved |
| replace physics-only SfP with physics-based deep learning | Miyazaki et al. · Deep SfP test set, whole set | mean angular error (degrees): 47.51 -> 18.52 | Improved |
| vary lighting (indoor, overcast, sunlight) | Proposed · Deep SfP dataset | mean angular error (degrees) | No clear effect |
Closest papers by meaning
- Deep Polarization Imaging for 3D Shape and SVBRDF Acquisition (CVPR 2021 · similarity 0.91)
- Shape From Polarization for Complex Scenes in the Wild (CVPR 2022 · similarity 0.90)
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 2025 · similarity 0.89)
- SfPUEL: Shape from Polarization under Unknown Environment Light (NeurIPS 2024 · similarity 0.88)
- Glossy Object Reconstruction with Cost-effective Polarized Acquisition (CVPR 2025 · similarity 0.86)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.85)
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.
