PSNR: 24.38SSIM: 0.641
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: 38.91SSIM: 0.9646
PSNR: 38.72SSIM: 0.9635
PSNR: 25.06SSIM: 0.607
PSNR: 39.14SSIM: 0.9658
PSNR: 23.6SSIM: 0.5728LRPSNR: 47.12NIQE: 5.49
PSNR: 38.62SSIM: 0.963
PSNR: 27.78SSIM: 0.7446
PSNR: 25.04SSIM: 0.6075
PSNR: 38.74
PSNR: 27.82SSIM: 0.744
PSNR: 24.93SSIM: 0.602
PSNR: 38.87SSIM: 0.9663
PSNR: 38.95SSIM: 0.9649
PSNR: 38.28SSIM: 0.9616
PSNR: 25.43
PSNR: 38.33
CRNN Overall Accuracy: 58.3ASTER Overall Accuracy: 68.1MORAN Overall Accuracy: 64.6Average Accuracy: 63.7
PSNR: 38.63SSIM: 0.9632