PSNR: 23.56SSIM: 0.6241LRPSNR: 42.66LPIPS: 0.2403
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: 28.00SSIM: 0.78LPIPS: 0.105LRPSNR: 47.3
#params (K): 1259FLOPs(G): 165.7
PSNR: 28.74SSIM: 0.8297LPIPS: 0.0753DISTS: 0.0795
PSNR: 29.137SSIM: 0.8023LPIPS: 0.0893DISTS: 0.0459
PSNR: 28.23SSIM: 0.912
PSNR: 30.188SSIM: 0.824MS-SSIM: 0.961LLE: 2.003
PSNR: 27.134SSIM: 0.741MS-SSIM: 0.935LLE: 2.261
PSNR: 29.577SSIM: 0.827MS-SSIM: 0.953LLE: 2.066
PSNR: 30.824SSIM: 0.838MS-SSIM: 0.971LLE: 2.071
PSNR: 29.77SSIM: 0.84
PSNR: 26.71SSIM: 0.65
PSNR: 31.26
PSNR: 29.78
PSNR: 27.33SSIM: 0.76LPIPS: 0.112
LPIPS: 0.321
PSNR: 24.03LPIPS: 0.345
PSNR: 27.494SSIM: 0.735MS-SSIM: 0.935LLE: 2.269
PSNR: 28.41SSIM: 0.804LPIPS: 0.104
PSNR: 27.09SSIM: 0.76LPIPS: 0.12LRPSNR: 49.96
PSNR: 25.463SSIM: 0.729MS-SSIM: 0.913LLE: 2.333
PSNR: 28.750SSIM: 0.806MS-SSIM: 0.952LLE: 2.702