Image Restoration by Deep Projected GSURE
This work provides an improved internal learning method for image restoration, benefiting researchers and practitioners dealing with ill-posed inverse problems in image processing, especially when external training data is scarce or observation models vary.
This paper addresses image restoration for ill-posed inverse problems by introducing a new framework that minimizes a projected-version of the Generalized Stein Unbiased Risk Estimator (GSURE) loss function, with the latent image parameterized by a CNN. The method outperforms other internal learning approaches like Deep Image Prior (DIP) when no explicit prior is used, and improves performance when integrated into plug-and-play prior schemes.
Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. In recent years, solutions that are based on deep Convolutional Neural Networks (CNNs) have shown great promise. Yet, most of these techniques, which train CNNs using external data, are restricted to the observation models that have been used in the training phase. A recent alternative that does not have this drawback relies on learning the target image using internal learning. One such prominent example is the Deep Image Prior (DIP) technique that trains a network directly on the input image with a least-squares loss. In this paper, we propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN. We demonstrate two ways to use our framework. In the first one, where no explicit prior is used, we show that the proposed approach outperforms other internal learning methods, such as DIP. In the second one, we show that our GSURE-based loss leads to improved performance when used within a plug-and-play priors scheme.