Image Denoising Based on Non-parametric ADMM Algorithm

Abstract

Image denoising is one of the most important tasks in image processing. In this paper, we propose a new method called Non-ParaMetric Alternating Direction Method of Multiplier (ADMM) algorithm (NPM-ADMM). We utilize the standard ADMM algorithm to solve the noisy image model and update the parameters via back propagation by minimizing the loss function. In contrast to the previous methods which are required to set the parameters carefully to approach better results, the proposed method can automatically learn the related parameters without the need of manually specifying. Furthermore, the filter coefficients and the nonlinear function in the regularization term are also learned together with the parameters, rather than fixed. Experiments on image denoising demonstrate our superior results with fast convergence speed and high restoration quality.