An Algorithm Unrolling Approach to Deep Image Deblurring

Yuelong Li, Mohammad Tofighi, Vishal Monga, Yonina C. Eldar

Research output: Contribution to journalArticle

Abstract

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.
Original languageEnglish
Article number1902.05399
Number of pages5
JournalarXiv
StateSubmitted - 9 Feb 2019
Externally publishedYes

Fingerprint

Dive into the research topics of 'An Algorithm Unrolling Approach to Deep Image Deblurring'. Together they form a unique fingerprint.

Cite this