CASIA OpenIR  > 智能制造技术与系统研究中心  > 多维数据分析
Single-image blind deblurring for non-uniform camera-shake blur
Xu Yuquan; Wang Lu; Hu Xiyuan; Peng Silong
Conference Name11th Asian Conference on Computer Vision ACCV 2012
Pagespp 336-348
Conference Date2012/11/5-2012/11/9
Conference Place韩国Daejeon Korea Republic of Korea
AbstractIn this paper we address the problem of estimating latent sharp image and unknown blur kernel from a single motion-blurred image. The blur results from camera shake and is spatially variant. Meanwhile the blur kernel of motion has three degrees of freedom i.e. translations and in-plane rotation. In order to solve this problem we first analyzed the homography blur model for the non-uniform camera-shake blur. We simplified the model to 3-dimensional camera motion which can be accelerated by exploiting the fast Fourier transform to process subsequent image deconvolution. We then proposed an effective method to handle the blind image-deblurring problem by the image decomposition which does not need to segment the image into local subregions under the assumption of spatially invariant blur. Experimental results on both synthetic and real blurred images show that the presented approach can successfully remove various kinds of blur.
Document Type会议论文
Corresponding AuthorXu Yuquan
Recommended Citation
GB/T 7714
Xu Yuquan,Wang Lu,Hu Xiyuan,et al. Single-image blind deblurring for non-uniform camera-shake blur[C],2013:pp 336-348.
Files in This Item:
File Name/Size DocType Version Access License
Single-image blind d(1706KB)会议论文 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xu Yuquan]'s Articles
[Wang Lu]'s Articles
[Hu Xiyuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xu Yuquan]'s Articles
[Wang Lu]'s Articles
[Hu Xiyuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xu Yuquan]'s Articles
[Wang Lu]'s Articles
[Hu Xiyuan]'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.