Enhanced Super-Resolution Generative Adversarial Networks: Difference between revisions

From Civitai Wiki
Jump to navigation Jump to search
(Created page with "Pipeine for Image Super-Resolution task that based on a frequently cited paper, ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks (Wang Xintao et al.), published in 2018. In few words, image super-resolution (SR) techniques reconstruct a higher-resolution (HR) image or sequence from the observed lower-resolution (LR) images, e.g. upscaling of 720p image into 1080p.")
 
No edit summary
Line 1: Line 1:
Pipeine for Image Super-Resolution task that based on a frequently cited paper, ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks (Wang Xintao et al.), published in 2018.
Pipeline for Image Super-Resolution, based upon ''ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks (Wang Xintao et al.)'', published in 2018.


In few words, image super-resolution (SR) techniques reconstruct a higher-resolution (HR) image or sequence from the observed lower-resolution (LR) images, e.g. upscaling of 720p image into 1080p.
Reconstructs a higher-resolution (HR) image or sequence from the observed lower-resolution (LR) images, e.g. [[Upscale|upscaling]] of 720p image into 1080p.

Revision as of 15:17, 11 October 2023

Pipeline for Image Super-Resolution, based upon ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks (Wang Xintao et al.), published in 2018.

Reconstructs a higher-resolution (HR) image or sequence from the observed lower-resolution (LR) images, e.g. upscaling of 720p image into 1080p.