Single-image blind deblurring for non-uniform camera-shake blur
Xu Yuquan; Wang Lu; Hu Xiyuan; Peng Silong
2013
会议名称11th Asian Conference on Computer Vision ACCV 2012
页码pp 336-348
会议日期2012/11/5-2012/11/9
会议地点韩国Daejeon Korea Republic of Korea
摘要In 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.
关键词
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12873
专题智能制造技术与系统研究中心_多维数据分析
通讯作者Xu Yuquan
推荐引用方式
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.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Single-image blind d(1706KB)会议论文 暂不开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xu Yuquan]的文章
[Wang Lu]的文章
[Hu Xiyuan]的文章
百度学术
百度学术中相似的文章
[Xu Yuquan]的文章
[Wang Lu]的文章
[Hu Xiyuan]的文章
必应学术
必应学术中相似的文章
[Xu Yuquan]的文章
[Wang Lu]的文章
[Hu Xiyuan]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。