Block-Matching Convolutional Neural Network for Image Denoising

TL;DR

This paper introduces BMCNN, a novel image denoising method that combines non-local self similarity priors with convolutional neural networks, effectively restoring both repetitive and irregular image structures.

Contribution

The paper proposes a new block-matching CNN approach that integrates NSS prior with CNN for improved image denoising performance.

Findings

Achieves state-of-the-art denoising results.

Effectively restores both repetitive and irregular structures.

Uses a denoised image as a pilot for block matching.

Abstract

There are two main streams in up-to-date image denoising algorithms: non-local self similarity (NSS) prior based methods and convolutional neural network (CNN) based methods. The NSS based methods are favorable on images with regular and repetitive patterns while the CNN based methods perform better on irregular structures. In this paper, we propose a block-matching convolutional neural network (BMCNN) method that combines NSS prior and CNN. Initially, similar local patches in the input image are integrated into a 3D block. In order to prevent the noise from messing up the block matching, we first apply an existing denoising algorithm on the noisy image. The denoised image is employed as a pilot signal for the block matching, and then denoising function for the block is learned by a CNN structure. Experimental results show that the proposed BMCNN algorithm achieves state-of-the-art performance. In detail, BMCNN can restore both repetitive and irregular structures.