Selective Residual M-Net for Real Image Denoising

TL;DR

This paper introduces SRMNet, a hierarchical residual network with selective kernels for improved blind real image denoising, achieving competitive results on synthetic and real-world datasets.

Contribution

The paper proposes a novel hierarchical residual network with selective kernels for real image denoising, enhancing multi-scale semantic information and performance.

Findings

Achieves competitive results on synthetic noisy datasets.

Performs well on real-world noisy datasets.

Outperforms traditional methods in quantitative metrics and visual quality.

Abstract

Image restoration is a low-level vision task which is to restore degraded images to noise-free images. With the success of deep neural networks, the convolutional neural networks surpass the traditional restoration methods and become the mainstream in the computer vision area. To advance the performanceof denoising algorithms, we propose a blind real image denoising network (SRMNet) by employing a hierarchical architecture improved from U-Net. Specifically, we use a selective kernel with residual block on the hierarchical structure called M-Net to enrich the multi-scale semantic information. Furthermore, our SRMNet has competitive performance results on two synthetic and two real-world noisy datasets in terms of quantitative metrics and visual quality. The source code and pretrained model are available at https://github.com/TentativeGitHub/SRMNet.