PSNR: 24.64SSIM: 0.71MOS: 1.2
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: 25.71SSIM: 0.813
FID: 147.21MS-SSIM: 0.900PSNR: 23.12SSIM: 0.688
FID: 139.78MS-SSIM: 0.930PSNR: 22.45SSIM: 0.709
SSIM for 2x T2w: 0.9836PSNR 2x T2w: 38.65SSIM 4x T2w: 0.9240PSNR 4x T2w: 30.79
PSNR: 24.16SSIM: 0.70
SSIM for 2x T2w: 0.9863PSNR 2x T2w: 39.71SSIM 4x T2w: 0.9413PSNR 4x T2w: 32.05
FID: 74.43MS-SSIM: 0.958PSNR: 27.42SSIM: 0.816
SSIM for 2x T2w: 0.9837PSNR 2x T2w: 38.67SSIM 4x T2w: 0.9210PSNR 4x T2w: 30.57
PSNR: 25.55SSIM: 0.8087
FID: 129.14MS-SSIM: 0.901PSNR: 22.47SSIM: 0.706
FID: 116.38MS-SSIM: 0.897PSNR: 23.64SSIM: 0.701
FID: 166.36MS-SSIM: 0.747PSNR: 15.43SSIM: 0.267
SSIM for 2x T2w: 0.9846PSNR 2x T2w: 39.09SSIM 4x T2w: 0.9312PSNR 4x T2w: 31.37
FID: 132.59MS-SSIM: 0.895PSNR: 21.96SSIM: 0.693
PSNR: 25.24SSIM: 0.802
FID: 5.36MS-SSIM: 0.971PSNR: 28.65SSIM: 0.816
PSNR: 25.29SSIM: 0.802
SSIM for 2x T2w: 0.9874PSNR 2x T2w: 40.30SSIM 4x T2w: 0.9472PSNR 4x T2w: 32.62
SSIM for 2x T2w: 0.9877PSNR 2x T2w: 40.43SSIM 4x T2w: 0.9469PSNR 4x T2w: 32.70
SSIM: 0.7946
PSNR: 15.74SSIM: 0.37
SSIM for 2x T2w: 0.9838PSNR 2x T2w: 38.75SSIM 4x T2w: 0.9324PSNR 4x T2w: 31.45
PSNR: 25.54SSIM: 0.8080
PSNR: 32.21SSIM: 0.9001
SSIM for 2x T2w: 0.8720PSNR 2x T2w: 29.38SSIM 4x T2w: 0.8500PSNR 4x T2w: 28.66