Selective Residual M-Net for Real Image Denoising
This work addresses image denoising for computer vision applications, but it is incremental as it builds on existing U-Net architectures.
The authors tackled real image denoising by proposing a blind denoising network called SRMNet, which uses a hierarchical architecture based on U-Net with selective kernel and residual blocks, achieving competitive performance on synthetic and real-world datasets.
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.