Efficient and Interpretable Deep Blind Image Deblurring Via Algorithm Unrolling

Blind image deblurring remains a topic of enduring interest. Learning based approaches, especially those that employ neural networks have emerged to complement traditional model based methods and in many cases achieve vastly enhanced performance. That said, neural network approaches are generally empirically designed and the underlying structures are difficult to interpret. In recent years, a promising technique called algorithm unrolling has been developed that has helped connect iterative algorithms such as those for sparse coding to neural network architectures. In this article, we propose a neural network architecture based on this idea. We first present an iterative algorithm that may be considered as a generalization of the traditional total-variation regularization method in the gradient domain. We then unroll the algorithm to construct a neural network for image deblurring which we refer to as Deep Unrolling for Blind Deblurring (DUBLID). Key algorithm parameters are learned with the help of training images. Our proposed deep network DUBLID achieves significant practical performance gains while enjoying interpretability and efficiency at the same time. Extensive experimental results show that DUBLID outperforms many state-of-the-art methods and in addition is computationally faster.

I. Introduction

Blind image deblurring refers to the process of recovering a sharp image from its blurred observation without explicitly knowing the blur function. In real world imaging, images frequently suffer from degraded quality as a consequence of blurring artifacts. Blind deblurring algorithms are designed to remove such artifacts. These distortions may come from different sources, such as atmospheric turbulence, diffraction, optical defocusing, camera shaking, and more [1]. In the computational imaging literature, motion deblurring is an important topic because camera shakes are common during the photography procedure. In recent years, this topic has attracted growing attention due to the popularity of smartphone cameras. On such platforms, the motion deblurring algorithm plays a crucial role because effective hardware solutions such as professional camera stabilizers are difficult to deploy due to cost and space restrictions.