In EDS ansehen

Cascaded Sliding-Window-Based Relativistic GAN Fusion for Perceptual and Consistent Video Super-Resolution

Gespeichert in:
Bibliographische Detailangaben
Titel: Cascaded Sliding-Window-Based Relativistic GAN Fusion for Perceptual and Consistent Video Super-Resolution
Autoren: Li, Dingyi
Weitere Verfasser: School of Computer Science and Engineering Nanjing, Nanjing University of Science and Technology (NJUST), Zhongzhi Shi, Michael Witbrock, Qi Tian, TC 12
Quelle: IFIP Advances in Information and Communication Technology ; 6th International Conference on Intelligence Science (ICIS) ; https://inria.hal.science/hal-05142880 ; 6th International Conference on Intelligence Science (ICIS), Oct 2024, Nanjing, China. pp.232-247, ⟨10.1007/978-3-031-71253-1_17⟩
Verlagsinformationen: CCSD
Springer Nature Switzerland
Publikationsjahr: 2024
Schlagwörter: Video Super-Resolution, Perceptual Quality, Temporal Consistency, Information Science, Intelligent Information Processing, [INFO]Computer Science [cs]
Geographisches Schlagwort: Nanjing, China
Beschreibung: Part 5: Perceptual Intelligence ; International audience ; Perceptual video super-resolution aims at converting low-resolution videos to visually appealing high-resolution ones. It may lead to temporal inconsistency due to the drastically changing outputs. In this paper, we propose cascaded sliding-window-based relativistic GAN (Generative Adversarial Network) fusion for perceptual and consistent video super-resolution (PC-VSR). Firstly, cascaded sliding-window-based relativistic GAN is designed to extract more useful information. It enlarges the temporal receptive field of sliding-window-based model in each step. It is able to enhance perceptual quality and compensate temporal consistency progressively and sufficiently. The trained separate refinement generator networks are fused into a final refinement generator. The final refinement generator can be calculated recursively at the testing stage. With our generator fusion, the parameter number is reduced and good quality is maintained. Extensive experimental results demonstrate that our approach outperforms state-of-the-art super-resolution methods in terms of perceptual quality. Our method also achieves good temporal consistency and per-pixel accuracy, compared with other perceptual approaches.
Publikationsart: conference object
Sprache: English
DOI: 10.1007/978-3-031-71253-1_17
Verfügbarkeit: https://inria.hal.science/hal-05142880
https://inria.hal.science/hal-05142880v1/document
https://inria.hal.science/hal-05142880v1/file/633143_1_En_17_Chapter.pdf
https://doi.org/10.1007/978-3-031-71253-1_17
Rights: http://creativecommons.org/licenses/by/
Dokumentencode: edsbas.7833912C
Datenbank: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://inria.hal.science/hal-05142880#
    Name: EDS - BASE (s4221598)
    Category: fullText
    Text: View record from BASE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Li%20D
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsbas
DbLabel: BASE
An: edsbas.7833912C
RelevancyScore: 907
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 907.306396484375
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Cascaded Sliding-Window-Based Relativistic GAN Fusion for Perceptual and Consistent Video Super-Resolution
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Li%2C+Dingyi%22">Li, Dingyi</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: School of Computer Science and Engineering Nanjing<br />Nanjing University of Science and Technology (NJUST)<br />Zhongzhi Shi<br />Michael Witbrock<br />Qi Tian<br />TC 12
– Name: TitleSource
  Label: Source
  Group: Src
  Data: IFIP Advances in Information and Communication Technology ; 6th International Conference on Intelligence Science (ICIS) ; https://inria.hal.science/hal-05142880 ; 6th International Conference on Intelligence Science (ICIS), Oct 2024, Nanjing, China. pp.232-247, ⟨10.1007/978-3-031-71253-1_17⟩
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: CCSD<br />Springer Nature Switzerland
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2024
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Video+Super-Resolution%22">Video Super-Resolution</searchLink><br /><searchLink fieldCode="DE" term="%22Perceptual+Quality%22">Perceptual Quality</searchLink><br /><searchLink fieldCode="DE" term="%22Temporal+Consistency%22">Temporal Consistency</searchLink><br /><searchLink fieldCode="DE" term="%22Information+Science%22">Information Science</searchLink><br /><searchLink fieldCode="DE" term="%22Intelligent+Information+Processing%22">Intelligent Information Processing</searchLink><br /><searchLink fieldCode="DE" term="%22[INFO]Computer+Science+[cs]%22">[INFO]Computer Science [cs]</searchLink>
– Name: Subject
  Label: Subject Geographic
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Nanjing%22">Nanjing</searchLink><br /><searchLink fieldCode="DE" term="%22China%22">China</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Part 5: Perceptual Intelligence ; International audience ; Perceptual video super-resolution aims at converting low-resolution videos to visually appealing high-resolution ones. It may lead to temporal inconsistency due to the drastically changing outputs. In this paper, we propose cascaded sliding-window-based relativistic GAN (Generative Adversarial Network) fusion for perceptual and consistent video super-resolution (PC-VSR). Firstly, cascaded sliding-window-based relativistic GAN is designed to extract more useful information. It enlarges the temporal receptive field of sliding-window-based model in each step. It is able to enhance perceptual quality and compensate temporal consistency progressively and sufficiently. The trained separate refinement generator networks are fused into a final refinement generator. The final refinement generator can be calculated recursively at the testing stage. With our generator fusion, the parameter number is reduced and good quality is maintained. Extensive experimental results demonstrate that our approach outperforms state-of-the-art super-resolution methods in terms of perceptual quality. Our method also achieves good temporal consistency and per-pixel accuracy, compared with other perceptual approaches.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: conference object
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1007/978-3-031-71253-1_17
– Name: URL
  Label: Availability
  Group: URL
  Data: https://inria.hal.science/hal-05142880<br />https://inria.hal.science/hal-05142880v1/document<br />https://inria.hal.science/hal-05142880v1/file/633143_1_En_17_Chapter.pdf<br />https://doi.org/10.1007/978-3-031-71253-1_17
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: http://creativecommons.org/licenses/by/
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.7833912C
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.7833912C
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/978-3-031-71253-1_17
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Nanjing
        Type: general
      – SubjectFull: China
        Type: general
      – SubjectFull: Video Super-Resolution
        Type: general
      – SubjectFull: Perceptual Quality
        Type: general
      – SubjectFull: Temporal Consistency
        Type: general
      – SubjectFull: Information Science
        Type: general
      – SubjectFull: Intelligent Information Processing
        Type: general
      – SubjectFull: [INFO]Computer Science [cs]
        Type: general
    Titles:
      – TitleFull: Cascaded Sliding-Window-Based Relativistic GAN Fusion for Perceptual and Consistent Video Super-Resolution
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Li, Dingyi
      – PersonEntity:
          Name:
            NameFull: School of Computer Science and Engineering Nanjing
      – PersonEntity:
          Name:
            NameFull: Nanjing University of Science and Technology (NJUST)
      – PersonEntity:
          Name:
            NameFull: Zhongzhi Shi
      – PersonEntity:
          Name:
            NameFull: Michael Witbrock
      – PersonEntity:
          Name:
            NameFull: Qi Tian
      – PersonEntity:
          Name:
            NameFull: TC 12
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-locals
              Value: edsbas
          Titles:
            – TitleFull: IFIP Advances in Information and Communication Technology ; 6th International Conference on Intelligence Science (ICIS) ; https://inria.hal.science/hal-05142880 ; 6th International Conference on Intelligence Science (ICIS), Oct 2024, Nanjing, China. pp.232-247, ⟨10.1007/978-3-031-71253-1_17⟩
              Type: main
ResultId 1