Title:	Improving Real-World Blind Super-Resolution
Authors:	Vo, Khoa D. Bui, Len T.
Citation:	WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 62-72.
Issue Date:	2023
Publisher:	Václav Skala - UNION Agency
Document type:	konferenční příspěvek conferenceObject
URI:	http://hdl.handle.net/11025/54400
ISBN:	978-80-86943-32-9
ISSN:	2464–4617 (print) 2464–4625 (CD/DVD)
Keywords:	slepé super-rozlišení;adaptivní degradace;duální ztráta vnímání;víceškálová diskriminace;degradace úpadku
Keywords in different language:	blind super-resolution;adaptive degradation;dual perceptual loss;multi-scale discriminato;dropout degradation;multi-scale discriminator
Abstract in different language:	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.
Rights:	© Václav Skala - UNION Agency
Appears in Collections:	WSCG 2023: Full Papers Proceedings

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.