Variational based Mixed Noise Removal with CNN Deep Learning Regularization

TL;DR

This paper introduces a novel variational-CNN hybrid approach for mixed noise removal in images, effectively classifying noise types and levels while enhancing image restoration quality.

Contribution

It combines variational methods with deep learning regularization to automatically classify and remove mixed noise, improving over existing techniques.

Findings

Achieves state-of-the-art results in mixed noise removal

Effectively classifies noise types and levels per pixel

Enhances image quality significantly compared to prior methods

Abstract

In this paper, the traditional model based variational method and learning based algorithms are naturally integrated to address mixed noise removal problem. To be different from single type noise (e.g. Gaussian) removal, it is a challenge problem to accurately discriminate noise types and levels for each pixel. We propose a variational method to iteratively estimate the noise parameters, and then the algorithm can automatically classify the noise according to the different statistical parameters. The proposed variational problem can be separated into regularization, synthesis, parameter estimation and noise classification four steps with the operator splitting scheme. Each step is related to an optimization subproblem. To enforce the regularization, the deep learning method is employed to learn the natural images priori. Compared with some model based regularizations, the CNN regularizer can significantly improve the quality of the restored images. Compared with some learning based methods, the synthesis step can produce better reconstructions by analyzing the recognized noise types and levels. In our method, the convolution neutral network (CNN) can be regarded as an operator which associated to a variational functional. From this viewpoint, the proposed method can be extended to many image reconstruction and inverse problems. Numerical experiments in the paper show that our method can achieve some state-of-the-art results for mixed noise removal.