Real Image Denoising with Feature Attention

TL;DR

This paper introduces RIDNet, a single-stage neural network that effectively denoises real photographs by leveraging feature attention and residual structures, outperforming existing methods in quality and robustness.

Contribution

It presents a novel single-stage blind denoising network with feature attention and residual on residual architecture for real-world image noise.

Findings

RIDNet outperforms 19 state-of-the-art algorithms on multiple datasets.

RIDNet achieves superior visual quality and quantitative metrics.

The model is effective on both synthetic and real noisy images.

Abstract

Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the practicability of denoising algorithms, this paper proposes a novel single-stage blind real image denoising network (RIDNet) by employing a modular architecture. We use a residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality on three synthetic and four real noisy datasets against 19 state-of-the-art algorithms demonstrate the superiority of our RIDNet.