Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/76277
Title: Beyond a Gaussian Denoiser : residual learning of deep CNN for image denoising
Authors: Zhang, K 
Zuo, WM
Chen, YJ
Meng, DY
Zhang, L 
Keywords: Image denoising
Convolutional neural networks
Residual learning
Batch normalization
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on image processing, 2017, v. 26, no. 7, p. 3142-3155 How to cite?
Journal: IEEE transactions on image processing 
Abstract: The discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks, such as Gaussian denoising, single image super-resolution, and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.
URI: http://hdl.handle.net/10397/76277
ISSN: 1057-7149
EISSN: 1941-0042
DOI: 10.1109/TIP.2017.2662206
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

59
Citations as of May 11, 2018

WEB OF SCIENCETM
Citations

38
Citations as of May 19, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.