NFCNN: Toward a Noise Fusion Convolutional Neural Network for Image Denoising

TL;DR

NFCNN introduces a multi-stage noise fusion CNN with fusion blocks for improved image denoising, achieving competitive results while preserving textures through a stage-wise training strategy.

Contribution

The paper proposes a novel multi-stage CNN with fusion blocks for image denoising, enhancing texture preservation and training stability.

Findings

Achieves competitive denoising performance compared to state-of-the-art methods.

Uses a fusion block to combine predicted clean and residual images.

Employs stage-wise supervised training to improve convergence.

Abstract

Deep learning based methods have achieved the state-of-the-art performance in image denoising. In this paper, a deep learning based denoising method is proposed and a module called fusion block is introduced in the convolutional neural network. For this so-called Noise Fusion Convolutional Neural Network (NFCNN), there are two branches in its multi-stage architecture. One branch aims to predict the latent clean image, while the other one predicts the residual image. A fusion block is contained between every two stages by taking the predicted clean image and the predicted residual image as a part of inputs, and it outputs a fused result to the next stage. NFCNN has an attractive texture preserving ability because of the fusion block. To train NFCNN, a stage-wise supervised training strategy is adopted to avoid the vanishing gradient and exploding gradient problems. Experimental results show that NFCNN is able to perform competitive denoising results when compared with some state-of-the-art algorithms.