PSNR: 27.59SSIM: 0.78
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: 29.25SSIM: 0.9017
FID: 60.67MS-SSIM: 0.807PSNR: 21.49SSIM: 0.515
FID: 23.97MS-SSIM: 0.951PSNR: 24.71SSIM: 0.804
PSNR: 22.50
FID: 12.4MS-SSIM: 0.971PSNR: 34.1SSIM: 0.906
PSNR: 21.84
FID: 19.07MS-SSIM: 0.934PSNR: 29.42SSIM: 0.832
FID: 72.73MS-SSIM: 0.782PSNR: 19.84SSIM: 0.353
PSNR: 25.57
FID: 17.14MS-SSIM: 0.931PSNR: 27.90SSIM: 0.822
PSNR: 29.24SSIM: 0.8383LPIPS: 0.239LRPSNR: 53.3
PSNR: 20.19
FID: 1.978MS-SSIM: 0.975PSNR: 33.04SSIM: 0.875
PSNR: 26.89SSIM: 0.7478LPIPS: 0.220
FID: 31.84MS-SSIM: 0.924PSNR: 27.40SSIM: 0.801
PSNR: 29SSIM: 0.89
PSNR: 30.65
PSNR: 24.10
PSNR: 29.14SSIM: 0.83LPIPS: 0.248
PSNR: 28.08SSIM: 0.8140
PSNR: 20.87