Image Deno sing via Multiscale Nonlinear Diffusion Models
Feng, Wensen1; Qiao, Peng2; Xi, Xuanyang3; Chen, Yunjin4
AbstractImage denoising is a fundamental operation in image processing and holds considerable practical importance for various real-world applications. Arguably several thousands of papers are dedicated to image denoising. In the past decade, state-of-the-art denoising algorithms have been clearly dominated by nonlocal patch-based methods, which explicitly exploit patch self-similarity within the targeted image. However, in the past two years, discriminatively trained local approaches have started to outperform previous nonlocal models and have been attracting increasing attention due to the additional advantage of computational efficiency. Successful approaches include cascade of shrinkage fields (CSF) and trainable nonlinear reaction diffusion (TNRD). These two methods are built on the filter response of linear filters of small size using feed forward architectures. Due to the locality inherent in local approaches, the CSF and TNRD models become less effective when the noise level is high and consequently introduce some noise artifacts. In order to overcome this problem, in this paper we introduce a multiscale strategy. To be specific, we build on our newly developed TNRD model, adopting the multiscale pyramid image representation to devise a multiscale nonlinear diffusion process. As expected, all the parameters in the proposed multiscale diffusion model, including the filters and the influence functions across scales, are learned from training data through a loss-based approach. Numerical results on Gaussian and Poisson denoising substantiate that the exploited multiscale strategy can successfully boost the performance of the original TNRD model with a single scale. As a consequence, the resulting multiscale diffusion models can significantly suppress the typical incorrect features for those noisy images with heavy noise. It turns out that multiscale TNRD variants achieve better performance than state-of-the-art denoising methods.
KeywordImage Denoising Multiscale Pyramid Image Representation Trainable Nonlinear Reaction Diffusion Model Gaussian Denoising Poisson Denoising
WOS HeadingsScience & Technology ; Technology ; Physical Sciences
Indexed BySCI
Funding OrganizationNational Natural Science Foundation of China(61602032)
WOS Research AreaComputer Science ; Mathematics ; Imaging Science & Photographic Technology
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Mathematics, Applied ; Imaging Science & Photographic Technology
WOS IDWOS:000412157400009
Citation statistics
Document Type期刊论文
Affiliation1.Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen, Peoples R China
2.Natl Univ Def Technol, Sch Comp, Natl Lab Parallel & Distributed Proc, Changsha 410073, Hunan, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
4.ULSee Inc, Hangzhou 310016, Zhejiang, Peoples R China
Recommended Citation
GB/T 7714
Feng, Wensen,Qiao, Peng,Xi, Xuanyang,et al. Image Deno sing via Multiscale Nonlinear Diffusion Models[J]. SIAM JOURNAL ON IMAGING SCIENCES,2017,10(3):1234-1257.
APA Feng, Wensen,Qiao, Peng,Xi, Xuanyang,&Chen, Yunjin.(2017).Image Deno sing via Multiscale Nonlinear Diffusion Models.SIAM JOURNAL ON IMAGING SCIENCES,10(3),1234-1257.
MLA Feng, Wensen,et al."Image Deno sing via Multiscale Nonlinear Diffusion Models".SIAM JOURNAL ON IMAGING SCIENCES 10.3(2017):1234-1257.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Feng, Wensen]'s Articles
[Qiao, Peng]'s Articles
[Xi, Xuanyang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Feng, Wensen]'s Articles
[Qiao, Peng]'s Articles
[Xi, Xuanyang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Feng, Wensen]'s Articles
[Qiao, Peng]'s Articles
[Xi, Xuanyang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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