Detail retaining convolutional neural network for image denoising
| Autor: | Shaobing Gao, Nianzu Lv, Xueyuan Wang, Shunli Wang, Juan Xiao, Yuanzheng Ye, Xiaoxia Li, Yingyue Zhou |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Generalization
business.industry Computer science Noise reduction Inpainting 020207 software engineering Pattern recognition 02 engineering and technology Residual Convolutional neural network Image (mathematics) Computer Science::Computer Vision and Pattern Recognition Signal Processing 0202 electrical engineering electronic engineering information engineering Media Technology 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence Electrical and Electronic Engineering Focus (optics) business Image restoration |
| Zdroj: | Journal of Visual Communication and Image Representation. 71:102774 |
| ISSN: | 1047-3203 |
| DOI: | 10.1016/j.jvcir.2020.102774 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect