Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/653268
Title: Image Deblurring via Enhanced Low-Rank Prior
Authors: Wenqi Ren;Xiaochun Cao;Jinshan Pan;Xiaojie Guo;Wangmeng Zuo;Ming-Hsuan Yang
subject: non-uniform deblurring|Blind deblurring|low rank|weighted nuclear norm
Year: 2016
Publisher: IEEE
Abstract: Low-rank matrix approximation has been successfully applied to numerous vision problems in recent years. In this paper, we propose a novel low-rank prior for blind image deblurring. Our key observation is that directly applying a simple low-rank model to a blurry input image significantly reduces the blur even without using any kernel information, while preserving important edge information. The same model can be used to reduce blur in the gradient map of a blurry input. Based on these properties, we introduce an enhanced prior for image deblurring by combining the low rank prior of similar patches from both the blurry image and its gradient map. We employ a weighted nuclear norm minimization method to further enhance the effectiveness of low-rank prior for image deblurring, by retaining the dominant edges and eliminating fine texture and slight edges in intermediate images, allowing for better kernel estimation. In addition, we evaluate the proposed enhanced low-rank prior for both the uniform and the non-uniform deblurring. Quantitative and qualitative experimental evaluations demonstrate that the proposed algorithm performs favorably against the state-of-the-art deblurring methods.
URI: http://localhost/handle/Hannan/137848
http://localhost/handle/Hannan/653268
ISSN: 1057-7149
1941-0042
volume: 25
issue: 7
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7473901.pdf10.02 MBAdobe PDFThumbnail
Preview File
Title: Image Deblurring via Enhanced Low-Rank Prior
Authors: Wenqi Ren;Xiaochun Cao;Jinshan Pan;Xiaojie Guo;Wangmeng Zuo;Ming-Hsuan Yang
subject: non-uniform deblurring|Blind deblurring|low rank|weighted nuclear norm
Year: 2016
Publisher: IEEE
Abstract: Low-rank matrix approximation has been successfully applied to numerous vision problems in recent years. In this paper, we propose a novel low-rank prior for blind image deblurring. Our key observation is that directly applying a simple low-rank model to a blurry input image significantly reduces the blur even without using any kernel information, while preserving important edge information. The same model can be used to reduce blur in the gradient map of a blurry input. Based on these properties, we introduce an enhanced prior for image deblurring by combining the low rank prior of similar patches from both the blurry image and its gradient map. We employ a weighted nuclear norm minimization method to further enhance the effectiveness of low-rank prior for image deblurring, by retaining the dominant edges and eliminating fine texture and slight edges in intermediate images, allowing for better kernel estimation. In addition, we evaluate the proposed enhanced low-rank prior for both the uniform and the non-uniform deblurring. Quantitative and qualitative experimental evaluations demonstrate that the proposed algorithm performs favorably against the state-of-the-art deblurring methods.
URI: http://localhost/handle/Hannan/137848
http://localhost/handle/Hannan/653268
ISSN: 1057-7149
1941-0042
volume: 25
issue: 7
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7473901.pdf10.02 MBAdobe PDFThumbnail
Preview File
Title: Image Deblurring via Enhanced Low-Rank Prior
Authors: Wenqi Ren;Xiaochun Cao;Jinshan Pan;Xiaojie Guo;Wangmeng Zuo;Ming-Hsuan Yang
subject: non-uniform deblurring|Blind deblurring|low rank|weighted nuclear norm
Year: 2016
Publisher: IEEE
Abstract: Low-rank matrix approximation has been successfully applied to numerous vision problems in recent years. In this paper, we propose a novel low-rank prior for blind image deblurring. Our key observation is that directly applying a simple low-rank model to a blurry input image significantly reduces the blur even without using any kernel information, while preserving important edge information. The same model can be used to reduce blur in the gradient map of a blurry input. Based on these properties, we introduce an enhanced prior for image deblurring by combining the low rank prior of similar patches from both the blurry image and its gradient map. We employ a weighted nuclear norm minimization method to further enhance the effectiveness of low-rank prior for image deblurring, by retaining the dominant edges and eliminating fine texture and slight edges in intermediate images, allowing for better kernel estimation. In addition, we evaluate the proposed enhanced low-rank prior for both the uniform and the non-uniform deblurring. Quantitative and qualitative experimental evaluations demonstrate that the proposed algorithm performs favorably against the state-of-the-art deblurring methods.
URI: http://localhost/handle/Hannan/137848
http://localhost/handle/Hannan/653268
ISSN: 1057-7149
1941-0042
volume: 25
issue: 7
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7473901.pdf10.02 MBAdobe PDFThumbnail
Preview File