Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/653268
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWenqi Renen_US
dc.contributor.authorXiaochun Caoen_US
dc.contributor.authorJinshan Panen_US
dc.contributor.authorXiaojie Guoen_US
dc.contributor.authorWangmeng Zuoen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.date.accessioned2020-05-20T10:19:34Z-
dc.date.available2020-05-20T10:19:34Z-
dc.date.issued2016en_US
dc.identifier.issn1057-7149en_US
dc.identifier.issn1941-0042en_US
dc.identifier.other10.1109/TIP.2016.2571062en_US
dc.identifier.urihttp://localhost/handle/Hannan/137848en_US
dc.identifier.urihttp://localhost/handle/Hannan/653268-
dc.description.abstractLow-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.en_US
dc.publisherIEEEen_US
dc.relation.haspart7473901.pdfen_US
dc.subjectnon-uniform deblurring|Blind deblurring|low rank|weighted nuclear normen_US
dc.titleImage Deblurring via Enhanced Low-Rank Prioren_US
dc.typeArticleen_US
dc.journal.volume25en_US
dc.journal.issue7en_US
dc.journal.titleIEEE Transactions on Image Processingen_US
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7473901.pdf10.02 MBAdobe PDFThumbnail
Preview File
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWenqi Renen_US
dc.contributor.authorXiaochun Caoen_US
dc.contributor.authorJinshan Panen_US
dc.contributor.authorXiaojie Guoen_US
dc.contributor.authorWangmeng Zuoen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.date.accessioned2020-05-20T10:19:34Z-
dc.date.available2020-05-20T10:19:34Z-
dc.date.issued2016en_US
dc.identifier.issn1057-7149en_US
dc.identifier.issn1941-0042en_US
dc.identifier.other10.1109/TIP.2016.2571062en_US
dc.identifier.urihttp://localhost/handle/Hannan/137848en_US
dc.identifier.urihttp://localhost/handle/Hannan/653268-
dc.description.abstractLow-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.en_US
dc.publisherIEEEen_US
dc.relation.haspart7473901.pdfen_US
dc.subjectnon-uniform deblurring|Blind deblurring|low rank|weighted nuclear normen_US
dc.titleImage Deblurring via Enhanced Low-Rank Prioren_US
dc.typeArticleen_US
dc.journal.volume25en_US
dc.journal.issue7en_US
dc.journal.titleIEEE Transactions on Image Processingen_US
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7473901.pdf10.02 MBAdobe PDFThumbnail
Preview File
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWenqi Renen_US
dc.contributor.authorXiaochun Caoen_US
dc.contributor.authorJinshan Panen_US
dc.contributor.authorXiaojie Guoen_US
dc.contributor.authorWangmeng Zuoen_US
dc.contributor.authorMing-Hsuan Yangen_US
dc.date.accessioned2020-05-20T10:19:34Z-
dc.date.available2020-05-20T10:19:34Z-
dc.date.issued2016en_US
dc.identifier.issn1057-7149en_US
dc.identifier.issn1941-0042en_US
dc.identifier.other10.1109/TIP.2016.2571062en_US
dc.identifier.urihttp://localhost/handle/Hannan/137848en_US
dc.identifier.urihttp://localhost/handle/Hannan/653268-
dc.description.abstractLow-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.en_US
dc.publisherIEEEen_US
dc.relation.haspart7473901.pdfen_US
dc.subjectnon-uniform deblurring|Blind deblurring|low rank|weighted nuclear normen_US
dc.titleImage Deblurring via Enhanced Low-Rank Prioren_US
dc.typeArticleen_US
dc.journal.volume25en_US
dc.journal.issue7en_US
dc.journal.titleIEEE Transactions on Image Processingen_US
Appears in Collections:2016

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