An Algorithm Unrolling Approach to Deep Image Deblurring
This addresses the problem of interpretability and performance in image deblurring for computer vision applications, but it is incremental as it extends existing unrolling ideas to a new domain.
The paper tackles blind image deblurring by proposing a neural network architecture based on algorithm unrolling, which connects iterative methods to deep learning, and reports that it outperforms many state-of-the-art methods.
While neural networks have achieved vastly enhanced performance over traditional iterative methods in many cases, they are generally empirically designed and the underlying structures are difficult to interpret. The algorithm unrolling approach has helped connect iterative algorithms to neural network architectures. However, such connections have not been made yet for blind image deblurring. In this paper, we propose a neural network architecture that advances this idea. We first present an iterative algorithm that may be considered a generalization of the traditional total-variation regularization method on the gradient domain, and subsequently unroll the half-quadratic splitting algorithm to construct a neural network. Our proposed deep network achieves significant practical performance gains while enjoying interpretability at the same time. Experimental results show that our approach outperforms many state-of-the-art methods.