Learning a Discriminative Prior for Blind Image Deblurring

TL;DR

This paper introduces a data-driven discriminative prior for blind image deblurring, using a CNN-based classifier within a MAP framework to effectively restore images across various scenarios.

Contribution

It proposes a novel CNN-based binary classifier prior integrated into a MAP framework for blind deblurring, with an efficient optimization method and extension to non-uniform deblurring.

Findings

Outperforms state-of-the-art algorithms in qualitative and quantitative tests

Effective across natural, face, text, and low-illumination images

Extensible to non-uniform deblurring scenarios

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 clear images over blurred images.In this work, we formulate the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN).The learned prior is able to distinguish whether an input image is clear or not.Embedded into the maximum a posterior (MAP) framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images.However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear CNN.Therefore, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient decent algorithm to solve the proposed model.Furthermore, the proposed model can be easily extended to non-uniform deblurring.Both qualitative and quantitative experimental results show that our method performs favorably against state-of-the-art algorithms as well as domain-specific image deblurring approaches.