atlas

Research map / Image generation / Image restoration

Robust Kernel Estimation With Outliers Handling for Image Deblurring

CVPR 2016 · Image generation › Image restoration · approach: Image deblurring · 113 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 outlier-aware restoration modelBlind deblurring · Saturated imagePSNR: 27.08 -> 27.48Helped
Use the proposed kernel estimate with [4] instead of its standard kernel estimate[4] non-blind restoration · Synthetic saturated image + impulse noisePSNR: 18.42 -> 22.72Helped
Use the proposed kernel estimate with [34] instead of its standard kernel estimate[34] non-blind restoration · Synthetic saturated image + impulse noisePSNR: +3.57Helped
Add outlier mask M during kernel estimation (ablation)Proposed method · Real image with saturated regionsvisual qualityHelped
Select reliable intermediate edges and remove detected outliers before estimating the kernelBlind deblurring methods · Images with saturated regionskernel estimation qualityHelped
Use the proposed outlier-aware latent-image restoration model rather than TV-L1Final latent image restoration · Saturated imagePSNR: 19.45 -> 27.48Helped

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