Detail retaining convolutional neural network for image denoising |
| |
| Affiliation: | 1. Robot Technology Used for Special Environment Key Laboratory of Sichuan Province, School of Information Engineering, Southwest University of Science and Technology, MianYang 621010, SiChuan, People’s Republic of China;2. College of Computer Science, Sichuan University, Chengdu 610065, SiChuan, People’s Republic of China;1. Haian Senior School of Jiangsu Province, Nantong 226600, China;2. College of Physical Education, China University of Mining and Technology, Xuzhou 221000, China;1. School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454001, China;2. School of Computer Science, Shaanxi Normal University, Xi’an 710119, China;3. School of Computer Science and Technology, Nanjing Normal University, Nanjing 210046, China;4. College of Electronics and Information Engineering, Shaanxi University of Science and Technology, Xi’an 710021, China;1. College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China;2. State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China;1. Institute of Computing, University of Campinas, Campinas, SP 13083-852, Brazil;2. Department of Informatics, Universidade Federal do Paraná, Curitiba, PR 81531-980, Brazil |
| |
| Abstract: | Compared with the traditional image denoising method, although the convolutional neural network (CNN) has better denoising performance, there is an important issue that has not been well resolved: the residual image obtained by learning the difference between noisy image and clean image pairs contains abundant image detail information, resulting in the serious loss of detail in the denoised image. In this paper, in order to relearn the lost image detail information, a mathematical model is deducted from a minimization problem and an end-to-end detail retaining CNN (DRCNN) is proposed. Unlike most denoising methods based on CNN, DRCNN is not only focus to image denoising, but also the integrity of high frequency image content. DRCNN needs less parameters and storage space, therefore it has better generalization ability. Moreover, DRCNN can also adapt to different image restoration tasks such as blind image denoising, single image superresolution (SISR), blind deburring and image inpainting. Extensive experiments show that DRCNN has a better effect than some classic and novel methods. |
| |
| Keywords: | Image denoising Convolutional neural network Detail retaining Image restoration Gaussian denoising |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
