Please use this identifier to cite or link to this item:
Title: On combining cnn with non-local self-similarity based image denoising methods
Authors: Yan, ZF
Guo, S 
Xiao, G
Zhang, HZ
Issue Date: 2020
Source: IEEE access, 2020, v. 8, p. 14789-14797
Abstract: Despite the significant advances in convolutional neural network (CNN) based image denoising, the existing methods still cannot consistently outperform non-local self-similarity (NSS) based methods, especially on images with many repetitive structures. Although several studies have been given to incorporate NSS priors with CNN-based denoising,their improvement is generally insignificant when compared with the state-of-the-art CNN-based denoisers. In this paper, we suggest to combine CNN and NSS based methods for improved image denoising, resulting in an NSS-UNet architecture. Motivated by gradient descent inference of TNRD, both the current estimate and noisy observation are considered as the inputs to the CNN. To take the NSS prior into account, the result by NSS (e.g., BM3D or WNNM), is adopted as the initial estimate. And a modified UNet is presented for exploiting the multi-scale information. We evaluate the proposed method on three common testing datasets. The results clearly show that NSS-UNet outperforms the existing CNN and NSS based methods in terms of both PSNR index and visual quality.
Keywords: Non-local self-similarity
Convolutional neural network
Residual learning
Image denoising
Publisher: Institute of Electrical and Electronics Engineers
Journal: IEEE access 
EISSN: 2169-3536
DOI: 10.1109/ACCESS.2019.2962809
Rights: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see
The following publication Z. Yan, S. Guo, G. Xiao and H. Zhang, "On Combining CNN With Non-Local Self-Similarity Based Image Denoising Methods," in IEEE Access, vol. 8, pp. 14789-14797, 2020 is available at
Appears in Collections:Journal/Magazine Article

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

Page view(s)

Citations as of Jul 8, 2020

Google ScholarTM



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