View in EDS HTML Full Text PDF Full Text

Video restoration with a deep plug-and-play prior.

Saved in:
Bibliographic Details
Title: Video restoration with a deep plug-and-play prior.
Authors: Monod, Antoine1,2 (AUTHOR) amonod@gopro.com, Delon, Julie1 (AUTHOR) julie.delon@u-paris.fr, Almansa, Andrés1 (AUTHOR) andres.almansa@u-paris.fr, Coupeté, Eva2 (AUTHOR) eva.coupete@gmail.com, Tassano, Matias3 (AUTHOR) tasso.matias@gmail.com
Source: EURASIP Journal on Image & Video Processing. 3/19/2026, Vol. 2026 Issue 1, p1-24. 24p.
Subjects: Embedded computer systems, Deep learning, High resolution imaging, Image denoising, Interpolation, Algorithms, Image enhancement (Imaging systems)
Abstract: Performing video restoration in embedded systems is a challenge. Indeed, state-of-the-art learning-based methods in video restoration are specifically trained for given tasks, and often rely on huge networks, which makes them unsuitable when memory and computing resources are limited. In this paper, we explore the use of deep Plug-and-Play (PnP) algorithms for video restoration. We distinguish ourselves from prior PnP work by directly writing PnP schemes on video sequences instead of separate images. Our experiments in video deblurring, super-resolution (SR), and pixel interpolation all show a clear benefit to using a network specifically designed for video denoising, as it yields better restoration performance than a single image network with similar denoising performance using the same PnP formulation, and more temporal stability than other image-based PnP works. Experiments also highlight that, while not always as effective as state-of-the-art single-task deep networks, our lightweight approach remains competitive for many video restoration tasks. [ABSTRACT FROM AUTHOR]
Copyright of EURASIP Journal on Image & Video 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: 193005333
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Video restoration with a deep plug-and-play prior.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Monod%2C+Antoine%22">Monod, Antoine</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> amonod@gopro.com</i><br /><searchLink fieldCode="AR" term="%22Delon%2C+Julie%22">Delon, Julie</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> julie.delon@u-paris.fr</i><br /><searchLink fieldCode="AR" term="%22Almansa%2C+Andrés%22">Almansa, Andrés</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> andres.almansa@u-paris.fr</i><br /><searchLink fieldCode="AR" term="%22Coupeté%2C+Eva%22">Coupeté, Eva</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> eva.coupete@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Tassano%2C+Matias%22">Tassano, Matias</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> tasso.matias@gmail.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22EURASIP+Journal+on+Image+%26+Video+Processing%22">EURASIP Journal on Image & Video Processing</searchLink>. 3/19/2026, Vol. 2026 Issue 1, p1-24. 24p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Embedded+computer+systems%22">Embedded computer systems</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22High+resolution+imaging%22">High resolution imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Image+denoising%22">Image denoising</searchLink><br /><searchLink fieldCode="DE" term="%22Interpolation%22">Interpolation</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Image+enhancement+%28Imaging+systems%29%22">Image enhancement (Imaging systems)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Performing video restoration in embedded systems is a challenge. Indeed, state-of-the-art learning-based methods in video restoration are specifically trained for given tasks, and often rely on huge networks, which makes them unsuitable when memory and computing resources are limited. In this paper, we explore the use of deep Plug-and-Play (PnP) algorithms for video restoration. We distinguish ourselves from prior PnP work by directly writing PnP schemes on video sequences instead of separate images. Our experiments in video deblurring, super-resolution (SR), and pixel interpolation all show a clear benefit to using a network specifically designed for video denoising, as it yields better restoration performance than a single image network with similar denoising performance using the same PnP formulation, and more temporal stability than other image-based PnP works. Experiments also highlight that, while not always as effective as state-of-the-art single-task deep networks, our lightweight approach remains competitive for many video restoration tasks. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of EURASIP Journal on Image & Video 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=193005333
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1186/s13640-025-00669-0
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 1
    Subjects:
      – SubjectFull: Embedded computer systems
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: High resolution imaging
        Type: general
      – SubjectFull: Image denoising
        Type: general
      – SubjectFull: Interpolation
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Image enhancement (Imaging systems)
        Type: general
    Titles:
      – TitleFull: Video restoration with a deep plug-and-play prior.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Monod, Antoine
      – PersonEntity:
          Name:
            NameFull: Delon, Julie
      – PersonEntity:
          Name:
            NameFull: Almansa, Andrés
      – PersonEntity:
          Name:
            NameFull: Coupeté, Eva
      – PersonEntity:
          Name:
            NameFull: Tassano, Matias
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 19
              M: 03
              Text: 3/19/2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 16875176
          Numbering:
            – Type: volume
              Value: 2026
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: EURASIP Journal on Image & Video Processing
              Type: main
ResultId 1