Blind Motion Deblurring with Cycle Generative Adversarial Networks
This addresses the problem of recovering sharp images from blurred inputs without prior knowledge of the blur process, which is incremental as it builds on existing deep learning methods.
The paper tackles blind motion deblurring by proposing a novel end-to-end learning model based on generative adversarial networks with new training strategies, achieving competitive performance on benchmark datasets by capturing high-frequency features well.
Blind motion deblurring is one of the most basic and challenging problems in image processing and computer vision. It aims to recover a sharp image from its blurred version knowing nothing about the blur process. Many existing methods use Maximum A Posteriori (MAP) or Expectation Maximization (EM) frameworks to deal with this kind of problems, but they cannot handle well the figh frequency features of natural images. Most recently, deep neural networks have been emerging as a powerful tool for image deblurring. In this paper, we prove that encoder-decoder architecture gives better results for image deblurring tasks. In addition, we propose a novel end-to-end learning model which refines generative adversarial network by many novel training strategies so as to tackle the problem of deblurring. Experimental results show that our model can capture high frequency features well, and the results on benchmark dataset show that proposed model achieves the competitive performance.