Semi-blind image deblurring by a proximal alternating minimization method with convergence guarantees

Abstract

The semi-blind image deblurring problem aims to simultaneously estimate the clean image and the point spread function (PSF), which results in a (jointly) nonconvex optimization problem. In this paper, we develop an efficient algorithm to tackle the corresponding minimization problem based on the framework of the proximal alternating minimization (PAM). We also establish the convergence of the proposed algorithm under a mild assumption. Numerical experiments demonstrate our approach could obtain a more robust performance than the related state-of-the-art semi-blind image deblurring method.