Blind Image Deblurring via Deep Discriminative Priors

• Published in: International journal of computer vision Vol. 127; no. 8; pp. 1025 - 1043
• Main Authors: Li, Lerenhan, Pan, Jinshan, Lai, Wei-Sheng, Gao, Changxin, Sang, Nong, Yang, Ming-Hsuan
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.08.2019; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Artificial Intelligence; Artificial neural networks; Computer Imaging; Computer Science; Employee motivation; Image Processing and Computer Vision; Image processing systems; Mathematical models; Neural networks; Pattern Recognition; Pattern Recognition and Graphics; State of the art; Vision; Vision systems; Deep learning; Discriminative prior; Blind mage deblurring
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-018-01146-0

We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor sharp images over blurred ones. In this work, we formulate the image prior as a binary classifier using a deep convolutional neural network. The learned prior is able to distinguish whether an input image is sharp or not. Embedded into the maximum a posterior framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images, as well as non-uniform deblurring. However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear neural network. In this work, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient descent algorithm to optimize the proposed model. Furthermore, we extend the proposed model to handle image dehazing. Both qualitative and quantitative experimental results show that our method performs favorably against the state-of-the-art algorithms as well as domain-specific image deblurring approaches.