Research map / Image generation / Image restoration
Blind Deblurring for Saturated Images
Liang Chen, Jiawei Zhang, Songnan Lin, Faming Fang, Jimmy S. Ren
Check 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 the proposed latent map to model saturation rather than setting M = 1 (ablation) | blind deblurring for saturated images · Pan et al. low-light dataset [23] | error ratio | Improved |
| use the proposed latent map instead of the Whyte et al. clipping approximation (ablation) | blind deblurring for saturated images · Pan et al. low-light dataset [23] | success rate | Improved |
| use the proposed latent map instead of the saturated map from Chen et al. [4] (ablation) | blind deblurring for saturated images · Pan et al. low-light dataset [23] | error ratio | Improved |
| use the proposed blur model and MAP optimization framework | blind deblurring for saturated images · Hu et al. saturated dataset [11] | average SSIM: 0.7980 -> 0.8098 | Improved |
| use the proposed blur model and MAP optimization framework | blind deblurring for saturated images · Pan et al. low-light dataset [23] | success rate (error ratio under 2): 68.8% -> 100% | Improved |
| vary λ across the tested range (ablation) | blind deblurring for saturated images · Pan et al. low-light dataset [23] | kernel similarity | No clear effect |
| vary β across the tested range (ablation) | blind deblurring for saturated images · Pan et al. low-light dataset [23] | kernel similarity | No clear effect |
Closest papers by meaning
- Blind image deblurring with noise-robust kernel estimation (ECCV 2024 · similarity 0.92)
- Pixel Screening Based Intermediate Correction for Blind Deblurring (CVPR 2022 · similarity 0.91)
- Blind Noisy Image Deblurring Using Residual Guidance Strategy (ICCV 2025 · similarity 0.91)
- Surface-Aware Blind Image Deblurring (TPAMI 2019 · similarity 0.90)
- Convergence Analysis of MAP Based Blur Kernel Estimation (ICCV 2017 · similarity 0.90)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · similarity 0.89)
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.
