View in EDS HTML Full Text PDF Full Text

Enhanced Patch-Wise Maximal Gradient for Blind Image Deblurring.

Saved in:
Bibliographic Details
Title: Enhanced Patch-Wise Maximal Gradient for Blind Image Deblurring.
Authors: zhang, Zirui1 (AUTHOR) 321113010254@njust.edu.cn, Guo, Zheng1 (AUTHOR) guozheng1999@njust.edu.cn, Xu, Zhenhua2 (AUTHOR) xzh@njust.edu.cn, Wang, Chunyong1 (AUTHOR) wangcyong@njust.edu.cn, Lai, Jiancheng1 (AUTHOR) laijiancheng@njust.edu.cn, Ji, Yunjing1 (AUTHOR) jyunjing@njust.edu.cn, Li, Zhenhua1 (AUTHOR) lizhenhua@njust.edu.cn
Source: Circuits, Systems & Signal Processing. Aug2025, Vol. 44 Issue 8, p6227-6254. 28p.
Subjects: Distribution (Probability theory), Simplicity
Abstract: The maximum intensity and gradient values of non-overlapping patches significantly decrease during the blurring process. To address this issue, we propose an enhanced patch-wise maximum gradient (EPMG) prior for blind image deblurring. We evaluate the statistical distribution of EPMG using a real dataset and mathematically demonstrate its effectiveness. Based on the EPMG prior, we develop an effective deblurring model incorporating an L0 regularized EPMG prior and an L0 regularized gradient prior. Unlike previous priors, our EPMG prior considers both intensity and gradient information, enabling a more comprehensive distinction between clear and blurred images. Additionally, the non-overlapping patch design we adopt ensures sparsity and simplicity, significantly enhancing computational efficiency. Extensive experimental results demonstrate that our method yields superior visual quality and quantitative performance compared to several state-of-the-art methods, particularly in computational efficiency and restoration quality. [ABSTRACT FROM AUTHOR]
Copyright of Circuits, Systems & Signal Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 186621385
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Enhanced Patch-Wise Maximal Gradient for Blind Image Deblurring.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22zhang%2C+Zirui%22">zhang, Zirui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 321113010254@njust.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Guo%2C+Zheng%22">Guo, Zheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> guozheng1999@njust.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Xu%2C+Zhenhua%22">Xu, Zhenhua</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> xzh@njust.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Chunyong%22">Wang, Chunyong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wangcyong@njust.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lai%2C+Jiancheng%22">Lai, Jiancheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> laijiancheng@njust.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Ji%2C+Yunjing%22">Ji, Yunjing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jyunjing@njust.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Zhenhua%22">Li, Zhenhua</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lizhenhua@njust.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Circuits%2C+Systems+%26+Signal+Processing%22">Circuits, Systems & Signal Processing</searchLink>. Aug2025, Vol. 44 Issue 8, p6227-6254. 28p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Distribution+%28Probability+theory%29%22">Distribution (Probability theory)</searchLink><br /><searchLink fieldCode="DE" term="%22Simplicity%22">Simplicity</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The maximum intensity and gradient values of non-overlapping patches significantly decrease during the blurring process. To address this issue, we propose an enhanced patch-wise maximum gradient (EPMG) prior for blind image deblurring. We evaluate the statistical distribution of EPMG using a real dataset and mathematically demonstrate its effectiveness. Based on the EPMG prior, we develop an effective deblurring model incorporating an L0 regularized EPMG prior and an L0 regularized gradient prior. Unlike previous priors, our EPMG prior considers both intensity and gradient information, enabling a more comprehensive distinction between clear and blurred images. Additionally, the non-overlapping patch design we adopt ensures sparsity and simplicity, significantly enhancing computational efficiency. Extensive experimental results demonstrate that our method yields superior visual quality and quantitative performance compared to several state-of-the-art methods, particularly in computational efficiency and restoration quality. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Circuits, Systems & Signal Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=186621385
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00034-025-03106-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 28
        StartPage: 6227
    Subjects:
      – SubjectFull: Distribution (Probability theory)
        Type: general
      – SubjectFull: Simplicity
        Type: general
    Titles:
      – TitleFull: Enhanced Patch-Wise Maximal Gradient for Blind Image Deblurring.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: zhang, Zirui
      – PersonEntity:
          Name:
            NameFull: Guo, Zheng
      – PersonEntity:
          Name:
            NameFull: Xu, Zhenhua
      – PersonEntity:
          Name:
            NameFull: Wang, Chunyong
      – PersonEntity:
          Name:
            NameFull: Lai, Jiancheng
      – PersonEntity:
          Name:
            NameFull: Ji, Yunjing
      – PersonEntity:
          Name:
            NameFull: Li, Zhenhua
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 0278081X
          Numbering:
            – Type: volume
              Value: 44
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Circuits, Systems & Signal Processing
              Type: main
ResultId 1