On the First-Order Optimization Methods in Deep Image Prior

Abstract

Abstract Deep learning methods have state-of-the-art performances in many image restoration tasks. Their effectiveness is mostly related to the size of the dataset used for the training. Deep image prior (DIP) is an energy-function framework which eliminates the dependency on the training set, by considering the structure of a neural network as an handcrafted prior offering high impedance to noise and low impedance to signal. In this paper, we analyze and compare the use of different optimization schemes inside the DIP framework for the denoising task.