A Hybrid CNN for Image Denoising  

作　　者：Menghua Zheng Keyan Zhi Jiawen Zeng Chunwei Tian Lei You 

机构地区：[1]School of Software,Northwestern Polytechnical University,Xi’an,Shaanxi 710129,China [2]Research&Development Institute of Northwestern Polytechnical University in Shenzhen,Shenzhen 518057,China [3]Yangtze River Delta Research Institute,Northwestern Polytechnical University,Taicang 215400,China [4]School of Biomedical Informatics,University of Texas Houston Science Center at Houston,Houston,TX 77030,USA

出　　处：《Journal of Artificial Intelligence and Technology》2022年第3期93-99,共7页人工智能技术学报（英文）

基　　金：supported in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2021A1515110079;in part by the Fundamental Research Funds for the Central Universities under Grant D5000210966;in part by the Basic Research Plan in Taicang under Grant TC2021JC23.

摘　　要：Deep convolutional neural networks(CNNs)with strong learning abilities have been used in the field of image denoising.However,some CNNs depend on a single deep network to train an image denoising model,which will have poor performance in complex screens.To address this problem,we propose a hybrid denoising CNN(HDCNN).HDCNN is composed of a dilated block(DB),RepVGG block(RVB),feature refinement block(FB),and a single convolution.DB combines a dilated convolution,batch normalization(BN),common convolutions,and activation function of ReLU to obtain more context information.RVB uses parallel combination of convolution,BN,and ReLU to extract complementary width features.FB is used to obtain more accurate information via refining obtained feature from the RVB.A single convolution collaborates a residual learning operation to construct a clean image.These key components make the HDCNN have good performance in image denoising.Experiment shows that the proposed HDCNN enjoys good denoising effect in public data sets.

关 键 词：CNN dilated convolutions image denoising RepVGG 

分 类 号：O17[理学—数学]