Considering Image Information and Self-similarity: A Compositional Denoising Network

TL;DR

This paper introduces a compositional denoising network that effectively leverages image information and self-similarity, addressing limitations of residual learning to achieve state-of-the-art denoising results.

Contribution

It proposes a novel CDN with separate paths for image information and noise estimation, explicitly incorporating self-similarity into training for improved denoising.

Findings

Achieves state-of-the-art results in synthetic image denoising

Effectively utilizes image self-similarity during training

Outperforms existing CNN-based denoising methods

Abstract

Recently, convolutional neural networks (CNNs) have been widely used in image denoising. Existing methods benefited from residual learning and achieved high performance. Much research has been paid attention to optimizing the network architecture of CNN but ignored the limitations of residual learning. This paper suggests two limitations of it. One is that residual learning focuses on estimating noise, thus overlooking the image information. The other is that the image self-similarity is not effectively considered. This paper proposes a compositional denoising network (CDN), whose image information path (IIP) and noise estimation path (NEP) will solve the two problems, respectively. IIP is trained by an image-to-image way to extract image information. For NEP, it utilizes the image self-similarity from the perspective of training. This similarity-based training method constrains NEP to output a similar estimated noise distribution for different image patches with a specific kind of noise. Finally, image information and noise distribution information will be comprehensively considered for image denoising. Experiments show that CDN achieves state-of-the-art results in synthetic and real-world image denoising. Our code will be released on https://github.com/JiaHongZ/CDN.