Research map / 3D vision / Depth and stereo
DuRP: Dual-Stage Physics-Embedded Learning for Joint Radiance and Polarization Restoration
Zhenshuo Yang, Qian He, Zhiyuan Liu, Baojie Fan, Jiandong Tian
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 the generalized polarization model instead of the traditional model (ablation) | DuRP · SRPG test set | PSNR DoLP: 25.594 -> 28.803 | Improved |
| add the generalized polarization model instead of the traditional model (ablation) | DuRP · SRPG test set | PSNR S0: 28.244 -> 33.696 | Improved |
| add the generalized polarization model instead of the traditional model (ablation) | DuRP · SRPG test set | PSNR AoLP: 12.543 -> 19.431 | Improved |
| embed the physical model into the network instead of direct polarization prediction (ablation) | DuRP · SRPG test set | PSNR DoLP: 24.355 -> 28.803 | Improved |
| embed the physical model into the network instead of direct polarization prediction (ablation) | DuRP · SRPG test set | PSNR AoLP: 16.242 -> 19.431 | Improved |
| add the refinement network (ablation) | DuRP · SRPG test set | PSNR S0: 31.652 -> 33.696 | Improved |
| add the refinement network (ablation) | DuRP · SRPG test set | PSNR AoLP: 18.662 -> 19.431 | Improved |
| add the polarization physical model in the P-Stage (ablation) | DuRP · SRPG test set | PSNR DoLP: DoLP PSNR decreasing by 3.16 dB | Improved |
| add the polarization physical model in the P-Stage (ablation) | DuRP · SRPG test set | PSNR AoLP: AoLP PSNR decreasing by 2.65 dB | Improved |
| add physical models in both stages versus fully direct prediction (ablation) | DuRP · SRPG test set | PSNR DoLP: DoLP and AoLP PSNR dropping by 4.44 dB and 3.19 dB | Improved |
| use lightweight U-Net instead of Swin-T for AL-Net (ablation) | DuRP · SRPG test set | PSNR S0: 31.701 -> 33.700 | Improved |
| use FP16 AMP inference | DuRP · SRPG test set | FPS: 16.8 -> 26.4 | No clear effect |
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.
- Deformer — DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image (ICCV 2023) · better on 6 of 6 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
- Physics-Guided Reflection Separation From a Pair of Unpolarized and Polarized Images (TPAMI 2022 · similarity 0.87)
- PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation (NeurIPS 2026 · similarity 0.87)
- PolarFree: Polarization-based Reflection-Free Imaging (CVPR 2025 · similarity 0.86)
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 2025 · similarity 0.86)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.85)
- Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing (NeurIPS 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.
