Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorVo, Khoa D.
dc.contributor.authorBui, Len T.
dc.contributor.editorSkala, Václav
dc.date.accessioned2023-10-15T17:23:44Z
dc.date.available2023-10-15T17:23:44Z
dc.date.issued2023
dc.identifier.citationWSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 62-72.en
dc.identifier.isbn978-80-86943-32-9
dc.identifier.issn2464–4617 (print)
dc.identifier.issn2464–4625 (CD/DVD)
dc.identifier.urihttp://hdl.handle.net/11025/54400
dc.description.sponsorshipThis research is funded by Univer sity of Science, VNU-HCM project CNTT 2023-0en
dc.format11 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.subjectslepé super-rozlišenícs
dc.subjectadaptivní degradacecs
dc.subjectduální ztráta vnímánícs
dc.subjectvíceškálová diskriminacecs
dc.subjectdegradace úpadkucs
dc.titleImproving Real-World Blind Super-Resolutionen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedThe aim of blind super-resolution (SR) in computer vision is to improve the resolution of an image without prior knowledge of the degradation process that caused the image to be low-resolution. The State of the Art (SOTA) model Real-ESRGAN has advanced perceptual loss and produced visually compelling outcomes using more com plex degradation models to simulate real-world degradations. However, there is still room to improve the super resolved quality of Real-ESRGAN by implementing recent techniques. This research paper introduces StarSR GAN, a novel GAN model designed for blind super-resolution tasks that utilize 5 various architectures. Our model provides new SOTA performance with roughly 10% better on the MANIQA and AHIQ measures, as demonstrated by experimental comparisons with Real-ESRGAN. In addition, as a compact version, StarSRGAN Lite provides approximately 7.5 times faster reconstruction speed (real-time upsampling from 540p to 4K) but can still keep nearly 90% of image quality, thereby facilitating the development of a real-time SR experience for future research. Our codes are released at https://github.com/kynthesis/StarSRGAN.en
dc.subject.translatedblind super-resolutionen
dc.subject.translatedadaptive degradationen
dc.subject.translateddual perceptual lossen
dc.subject.translatedmulti-scale discriminatoen
dc.subject.translateddropout degradationen
dc.subject.translatedmulti-scale discriminatoren
dc.identifier.doihttps://www.doi.org/10.24132/CSRN.3301.9
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:WSCG 2023: Full Papers Proceedings

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
E23-full.pdfPlný text9,15 MBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/54400

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikace ZČU / UWB Publications
  3. Sborníky ZČU / UWB Proceedings
  4. WSCG: Full Papers
  5. WSCG 2023: Full Papers Proceedings