Selective Residual M-Net for Real Image Denoising

• DOI: 10.23919/eusipco55093.2022.9909521
• Publication Date: 2022-12-20T18:57:26Z
• Authors: Chi-Mao Fan; Tsung-Jung Liu; Kuan-Hsien Liu; Ching-Hsiang Chiu
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Artificial Intelligence; Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV); Computer Science - Computer Vision and Pattern Recognition; 02 engineering and technology; Electrical Engineering and Systems Science - Image and Video Processing; Machine Learning (cs.LG); Multimedia (cs.MM); Artificial Intelligence (cs.AI); FOS: Electrical engineering, electronic engineering, information engineering; 0202 electrical engineering, electronic engineering, information engineering; Computer Science - Multimedia

arXiv admin note: text overlap with arXiv:2203.01296<br/>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.<br/>