Blind Image Deblurring via Deep Discriminative Priors

Lerenhan Li, Jinshan Pan, Wei Sheng Lai, Changxin Gao, Nong Sang, Ming Hsuan Yang

Research output: Contribution to journalArticlepeer-review

44 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)1025-1043
Number of pages19
JournalInternational Journal of Computer Vision
Volume127
Issue number8
DOIs
Publication statusPublished - 2019 Aug 1

Bibliographical note

Funding Information:
This work is partially supported by the National Natural Science Foundation of China (Nos. 61433007 and 61872421), the National Science Foundation CAREER (No. 1149783), the Natural Science Foundation of Jiangsu Province (No. BK20180471), and gifts from Adobe and Nvidia. Lerenhan Li is supported by a scholarship from China Scholarship Council. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Funding Information:
This work is partially supported by the National Natural Science Foundation of China (Nos. 61433007 and 61872421), the National Science Foundation CAREER (No. 1149783), the Natural Science Foundation of Jiangsu Province (No. BK20180471), and gifts from Adobe and Nvidia. Lerenhan Li is supported by a scholarship from China Scholarship Council.

Publisher Copyright:
© 2019, Springer Science+Business Media, LLC, part of Springer Nature.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Blind Image Deblurring via Deep Discriminative Priors'. Together they form a unique fingerprint.

Cite this