Research map / Image generation / Image restoration
Learning to Deblur Polarized Images
Chu Zhou, Minggui Teng, Xinyu Zhou, Chao Xu, Imari Sato, Boxin Shi
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 two-stage pipeline with estimated I_guide (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of DoLP p: 27.12 -> 29.12 | Improved |
| add Stokes parameters S*1,2 as priors in stage one (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of DoLP p: 28.41 -> 29.12 | Improved |
| use Stokes S*1,2 rather than gradient distribution G as prior (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of DoLP p: 28.43 -> 29.12 | Improved |
| add SGSC in stage one (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of intensity I: 28.99 -> 29.67 | Improved |
| add SGSC in stage one (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of DoLP p: 29.11 -> 29.12 | No clear effect |
| add MCTE in stage two (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of AoLP theta: 17.17 -> 17.77 | Improved |
| add MCTE in stage two (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of intensity I: 29.38 -> 29.67 | Improved |
| add PG strategy (separate processing per polarized image) (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of AoLP theta: 17.52 -> 17.77 | Improved |
| add Stokes loss L_s (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of AoLP theta: 17.48 -> 17.77 | Improved |
| add Stokes loss L_s (ablation) | polarized deblurring network · Synthetic polarized deblurring test set | PSNR of DoLP p: 29.03 -> 29.12 | Improved |
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.
- XYDeblur — XYDeblur: Divide and Conquer for Single Image Deblurring (CVPR 2022) · better on 3 of 3 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
- Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing (NeurIPS 2024 · similarity 0.87)
- RGB-to-Polarization Estimation: A New Task and Benchmark Study (NeurIPS 2025 · similarity 0.85)
- PolarFree: Polarization-based Reflection-Free Imaging (CVPR 2025 · similarity 0.85)
- A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition (CVPR 2025 · similarity 0.85)
- PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution (CVPR 2025 · similarity 0.85)
- Learning to Remove Wrinkled Transparent Film with Polarized Prior (CVPR 2024 · similarity 0.83)
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.
