CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
Single-image motion deblurring using an adaptive image prior
He, Ning1; Lu, Ke2; Bao, Bing-Kun3; Zhang, Lu-Lu1; Wang, Jin-Bao1
Source PublicationINFORMATION SCIENCES
2014-10-10
Volume281Pages:736-749
SubtypeArticle
AbstractBlind deblurring is the restoration of a sharp image from a blurred image when the blur kernel is unknown. Most image deblurring algorithms impose a uniform sparse gradient prior on the whole image, and reconstruct the image with piecewise smooth characteristics. Although the sparse gradient prior removes ringing and noise artifacts, it inevitably removes mid-frequency structures, leading to poor visual quality. The gradient profile of fractal-like structures is close to a Gaussian distribution, and small gradients from such regions are severely penalized by the sparse gradient prior. In this paper, we introduce an image deblurring algorithm that adapts the image prior to the underlying detailed structures. The statistics of a local detailed structure can be different from those of the global structure. By identifying the correct image prior for each pixel in the image, our approach models the spatially varying motion blur exhibited by camera motion more effectively than conventional methods based on space-invariant blur kernels. Using different priors for the local region and the motion blur kernel, we derive a minimization energy function that alternates between blur kernel estimation and deblurring image restoration until convergence. Experimental results demonstrate that the proposed approach is efficient and effective in reducing motion blur in an arbitrary direction in a single image. (C) 2014 Elsevier Inc. All rights reserved.
KeywordMotion Deblurring Point Spread Function Adapting Image Prior Spatially Varying Motion
WOS HeadingsScience & Technology ; Technology
WOS KeywordBOUNDARY-CONDITIONS ; RESTORATION ; VIDEO
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems
WOS IDWOS:000340315600052
Citation statistics
Cited Times:3[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8031
Collection模式识别国家重点实验室_多媒体计算与图形学
Affiliation1.Beijing Union Univ, Coll Informat Technol, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing 100080, Peoples R China
Recommended Citation
GB/T 7714
He, Ning,Lu, Ke,Bao, Bing-Kun,et al. Single-image motion deblurring using an adaptive image prior[J]. INFORMATION SCIENCES,2014,281:736-749.
APA He, Ning,Lu, Ke,Bao, Bing-Kun,Zhang, Lu-Lu,&Wang, Jin-Bao.(2014).Single-image motion deblurring using an adaptive image prior.INFORMATION SCIENCES,281,736-749.
MLA He, Ning,et al."Single-image motion deblurring using an adaptive image prior".INFORMATION SCIENCES 281(2014):736-749.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He, Ning]'s Articles
[Lu, Ke]'s Articles
[Bao, Bing-Kun]'s Articles
Baidu academic
Similar articles in Baidu academic
[He, Ning]'s Articles
[Lu, Ke]'s Articles
[Bao, Bing-Kun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He, Ning]'s Articles
[Lu, Ke]'s Articles
[Bao, Bing-Kun]'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.