Good Regions to Deblur

Zhe Hu Ming-Hsuan Yang
UC Merced                

In Proc. of European Conference on Computer Vision (ECCV 2012)


The goal of single image deblurring is to recover both a latent clear image and an underlying blur kernel from one input blurred image. Recent works focus on exploiting natural image priors or additional image observations for deblurring, but pay less attention to the influence of image structures on estimating blur kernels. What is the useful image structure and how can one select good regions for deblurring? We formulate the problem of learning good regions for deblurring within the Conditional Random Field framework. To better compare blur kernels, we develop an effective similarity metric for labelling training samples. The learned model is able to predict good regions from an input blurred image for deblurring without user guidance. Qualitative and quantitative evaluations demonstrate that good regions can be selected by the proposed algorithms for effective image deblurring.

Paper and MATLAB code

The paper and MATLAB code can be found here. [PDF] [Supplemental material] [MATLAB code] [Dataset]

Notice: I have updated the code by fixing some bugs. Please refer to the updated code.


title = {Good Regions to Deblur},
author = {Zhe Hu and Ming-Hsuan Yang},
journal = {European Vision on Computer Vision (ECCV 2012)},
year = {2012}