Conference
Προβολή σε EDS

On the modifications of one method for rendering global illumination using a generative adversarial neural network.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: On the modifications of one method for rendering global illumination using a generative adversarial neural network.
Συγγραφείς: Rubinov, Kirill1 RubinovKA@mpei.ru, Frolov, Alexander1
Πηγή: EPJ Web of Conferences. 2/17/2025, Vol. 318, p1-8. 8p.
Θεματικοί όροι: *Program generators (Computer programs), *Convolutional neural networks, *Artificial neural networks, *Image quality analysis, *Image processing
Περίληψη: Three variants for modifying one method for rendering 3D scenes using a generative adversarial network are proposed to generate realistic lighting in screen space. Experiments using software implementations of neural networks have shown that adding 25% resolution ray traced rendering to the generator input improves image quality when assessed by both the SSIM structural similarity index and the peak signalto- noise ratio PSNR. Adding noise to the discriminator layers improves the quality of network performance in both respects, but not significantly. Passing the ray traced rendering to the hidden convolutional layers of the generator instead of the input leads to a decrease in quality in both metrics compared to other modifications, but avoids unwanted effects on the edges of objects. [ABSTRACT FROM AUTHOR]
Βάση Δεδομένων: Academic Search Index
FullText Links:
  – Type: other
Text:
  Availability: 0
Header DbId: asx
DbLabel: Academic Search Index
An: 183545174
RelevancyScore: 1369
AccessLevel: 6
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 1368.69799804688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: On the modifications of one method for rendering global illumination using a generative adversarial neural network.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Rubinov%2C+Kirill%22">Rubinov, Kirill</searchLink><relatesTo>1</relatesTo><i> RubinovKA@mpei.ru</i><br /><searchLink fieldCode="AR" term="%22Frolov%2C+Alexander%22">Frolov, Alexander</searchLink><relatesTo>1</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22EPJ+Web+of+Conferences%22">EPJ Web of Conferences</searchLink>. 2/17/2025, Vol. 318, p1-8. 8p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Program+generators+%28Computer+programs%29%22">Program generators (Computer programs)</searchLink><br />*<searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Image+quality+analysis%22">Image quality analysis</searchLink><br />*<searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Three variants for modifying one method for rendering 3D scenes using a generative adversarial network are proposed to generate realistic lighting in screen space. Experiments using software implementations of neural networks have shown that adding 25% resolution ray traced rendering to the generator input improves image quality when assessed by both the SSIM structural similarity index and the peak signalto- noise ratio PSNR. Adding noise to the discriminator layers improves the quality of network performance in both respects, but not significantly. Passing the ray traced rendering to the hidden convolutional layers of the generator instead of the input leads to a decrease in quality in both metrics compared to other modifications, but avoids unwanted effects on the edges of objects. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=183545174
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1051/epjconf/202531804010
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 1
    Subjects:
      – SubjectFull: Program generators (Computer programs)
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Image quality analysis
        Type: general
      – SubjectFull: Image processing
        Type: general
    Titles:
      – TitleFull: On the modifications of one method for rendering global illumination using a generative adversarial neural network.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Rubinov, Kirill
      – PersonEntity:
          Name:
            NameFull: Frolov, Alexander
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 17
              M: 02
              Text: 2/17/2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 21016275
          Numbering:
            – Type: volume
              Value: 318
          Titles:
            – TitleFull: EPJ Web of Conferences
              Type: main
ResultId 1