AI Paper Atlas

Research map / Image generation / Image restoration

Blind Image Deblurring With Outlier Handling

Jiangxin Dong, Jinshan Pan, Zhixun Su, Ming-Hsuan Yang

ICCV 2017 · Image generation › Image restoration · approach: Image deblurring · 103 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace heuristic edge selection and outlier detection with a robust data fidelity term (ours vs Pan et al. [22])blind deblurring · Synthetic saturated-pixel dataset (5 images x 8 kernels)Average error ratio: 3.22 -> 3.09Improved
use the robust data fidelity term instead of dark channel prior [23]blind deblurring · Synthetic saturated-pixel dataset (5 images x 8 kernels)Average error ratio: 3.83 -> 3.09Improved
use the robust data fidelity term instead of outlier handling [22]blind deblurring · Synthetic impulse-noise dataset (30 images x 8 kernels, density 0.02)Average PSNR: 32.0176 -> 34.5818Improved
use the robust data fidelity term instead of Xu et al. [33]blind deblurring · Synthetic impulse-noise dataset (30 images x 8 kernels, density 0.02)Average PSNR: 30.6736 -> 34.5818Improved
use the robust data fidelity term instead of Cho and Lee [3]blind deblurring · Synthetic saturated-pixel dataset (5 images x 8 kernels)Average error ratio: 18.04 -> 3.09Improved
use the robust data fidelity term instead of Hu et al. [8]blind deblurring · Synthetic saturated-pixel dataset (5 images x 8 kernels)Average error ratio: 34.37 -> 3.09Improved
apply the method to images without outliersblind deblurring · Benchmark datasets [16, 26] without outliersSuccess rate vs error ratioNo clear effect
increase impulse noise densityblind deblurring · Impulse noise datasetAverage PSNRNo clear effect
iterate the alternating optimizationblind deblurring · Impulse noise datasetAverage kernel similarity and energyImproved

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