PSNR: 35.71 ± 1.77
Papers with Code · CC BY-SA 4.0
Image-to-Image Translation
Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.
<span style="color:grey; opacity: 0.6">( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )</span>
논문
PSNR: 11.14SSIM: 0.21
mIoU: 75.6
Kernel Inception Distance: 11.61
10 way 1~2 shot: 457
mIoU: 70.0
Frechet Inception Distance: 38.06Number of params: 8.751M
Average PSNR: 21.12
FID: 51.04
Kernel Inception Distance: 11.40
mIoU: 73.8
PSNR: 4.19SSIM: 0.05
Kernel Inception Distance: 5.8
mIoU: 75.9
Frechet Inception Distance: 53.0Number of params: 15.9M
mIoU: 69.4
mIoU: 70.3
Frechet Inception Distance: 89.7Number of params: 28.2M
PSNR: 30.42