Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Vo, Khoa D. | |
dc.contributor.author | Bui, Len T. | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2023-10-15T17:23:44Z | |
dc.date.available | 2023-10-15T17:23:44Z | |
dc.date.issued | 2023 | |
dc.identifier.citation | WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 62-72. | en |
dc.identifier.isbn | 978-80-86943-32-9 | |
dc.identifier.issn | 2464–4617 (print) | |
dc.identifier.issn | 2464–4625 (CD/DVD) | |
dc.identifier.uri | http://hdl.handle.net/11025/54400 | |
dc.description.sponsorship | This research is funded by Univer sity of Science, VNU-HCM project CNTT 2023-0 | en |
dc.format | 11 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Václav Skala - UNION Agency | en |
dc.rights | © Václav Skala - UNION Agency | en |
dc.subject | slepé super-rozlišení | cs |
dc.subject | adaptivní degradace | cs |
dc.subject | duální ztráta vnímání | cs |
dc.subject | víceškálová diskriminace | cs |
dc.subject | degradace úpadku | cs |
dc.title | Improving Real-World Blind Super-Resolution | en |
dc.type | konferenční příspěvek | cs |
dc.type | conferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | The 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.translated | blind super-resolution | en |
dc.subject.translated | adaptive degradation | en |
dc.subject.translated | dual perceptual loss | en |
dc.subject.translated | multi-scale discriminato | en |
dc.subject.translated | dropout degradation | en |
dc.subject.translated | multi-scale discriminator | en |
dc.identifier.doi | https://www.doi.org/10.24132/CSRN.3301.9 | |
dc.type.status | Peer-reviewed | en |
Vyskytuje se v kolekcích: | WSCG 2023: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
E23-full.pdf | Plný text | 9,15 MB | Adobe PDF | Zobrazit/otevřít |
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.