Back to articles
Articles
Volume: 31 | Article ID: art00007
Image
GAN based image deblurring using dark channel prior
  DOI :  10.2352/ISSN.2470-1173.2019.13.COIMG-136  Published OnlineJanuary 2019
Abstract

A conditional general adversarial network (GAN) is proposed for image deblurring problem. It is tailored for image deblurring instead of just applying GAN on the deblurring problem. Motivated by that, dark channel prior is carefully picked to be incorporated into the loss function for network training. To make it more compatible with neuron networks, its original indifferentiable form is discarded and L2 norm is adopted instead. On both synthetic datasets and noisy natural images, the proposed network shows improved deblurring performance and robustness to image noise qualitatively and quantitatively. Additionally, compared to the existing end-to-end deblurring networks, our network structure is light-weight, which ensures less training and testing time.

Subject Areas :
Views 50
Downloads 11
 articleview.views 50
 articleview.downloads 11
  Cite this article 

Shuang Zhang*, Ada Zhen, Robert L. Stevenson, "GAN based image deblurring using dark channel priorin Proc. IS&T Int’l. Symp. on Electronic Imaging: Computational Imaging XVII,  2019,  pp 136-1 - 136-6,  https://doi.org/10.2352/ISSN.2470-1173.2019.13.COIMG-136

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2019
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA