Block-Matching Convolutional Neural Network for Image Denoising
This addresses image denoising for computer vision applications, but it is incremental as it hybridizes existing approaches.
The paper tackled image denoising by combining non-local self-similarity priors and convolutional neural networks into a block-matching CNN method, achieving state-of-the-art performance in restoring both repetitive and irregular structures.
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.