AI Paper Atlas

Research map / Image generation / Image restoration

Blind Deblurring for Saturated Images

Liang Chen, Jiawei Zhang, Songnan Lin, Faming Fang, Jimmy S. Ren

CVPR 2021 · Image generation › Image restoration · approach: Image deblurring · 49 citations (OpenAlex)

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 changedWhereMeasuredEffect
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 ratioImproved
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 rateImproved
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 ratioImproved
use the proposed blur model and MAP optimization frameworkblind deblurring for saturated images · Hu et al. saturated dataset [11]average SSIM: 0.7980 -> 0.8098Improved
use the proposed blur model and MAP optimization frameworkblind 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 similarityNo clear effect
vary β across the tested range (ablation)blind deblurring for saturated images · Pan et al. low-light dataset [23]kernel similarityNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy