PSNR: 33.09SSIM: 0.9335
Papers with Code · CC BY-SA 4.0
Image Super-Resolution
Image Super-Resolution is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.
논문
PSNR: 33.14SSIM: 0.9347
PSNR: 32.67SSIM: 0.9301
PSNR: 24SSIM: 0.6534LRPSNR: 41.36LPIPS: 0.2058
PSNR: 32.66SSIM: 0.9297
SSIM: 0.9022
PSNR: 32.68SSIM: 0.9303
PSNR: 32.85SSIM: 0.9318
PSNR: 31.78SSIM: 0.9211
PSNR: 31.68SSIM: 0.9226
NIQE: 2.55
PSNR: 33.13SSIM: 0.9366
PSNR: 33.19SSIM: 0.9344
PSNR: 31.79SSIM: 0.921
PSNR: 31.75SSIM: 0.9229
PSNR: 23.38LPIPS: 0.348
NIQE: 2.71
PSNR: 32.63SSIM: 0.9306
SSIM: 0.9211
NIQE: 2.51
PSNR: 31.66SSIM: 0.9222
PSNR: 32.83SSIM: 0.9314
PSNR: 32.22SSIM: 0.9273