Robust Unsupervised Deep Learning for Nonblind Image Deconvolution With Inaccurate Kernels.

Abstract

Nonblind image deconvolution/deblurring aims at restoring sharp images from their noisy blurred versions using an associated blur kernel with potential inaccuracy. Current deep learning (DL) models of nonblind image deconvolution (NBID) predominantly reply on ground truth (GT) images for supervision, which restricts their applicability to certain real-world scenarios such as scientific imaging. This article proposes a fully unsupervised DL approach for NBID, utilizing a GT-free end-to-end training process that adeptly handles both measurement noise and kernel error. Specifically, in the absence of GT images, a self-reconstruction loss is proposed to handle measurement noise, by effectively emulating its supervised counterpart. Recognizing the likely occurrence of kernel error during both training and testing data, we introduce a self-ensemble loss function and an ensemble inference scheme, anchored by a phase-keeping kernel perturbation strategy. Furthermore, a shifting mechanism is integrated so as to the loss functions to resolve the shift ambiguity caused by kernel error. Extensive experiments show the superiority of our proposed approach over existing unsupervised NBID methods, as well as its competitive performance against some of the recent supervised methods.