FID: 16.54LPIPS: 0.29
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
mIoU: 42.1Accuracy: 71.5FID: 19.1
FID: 13.73LPIPS: 0.428
Kernel Inception Distance: 8.15
FID: 13.3
FID: 14.3
FID: 9.97
Per-pixel Accuracy: 42%Per-class Accuracy: 22%Class IOU: 0.09
FID: 30.61
mIoU: 14.6Accuracy: 45.8%FID: 111.5
Per-pixel Accuracy: 70.0%Per-class Accuracy: 46.0%Class IOU: 0.26
FID: 23.8
mIoU: 41.6Accuracy: 70.7%FID: 19.2
FID: 15.8
mIoU: 23.7Accuracy: 40.4%FID: 70.4
Frechet Inception Distance: 134.4Number of Params: 15.9M
FID: 15.6
PSNR: 26.90
mIoU: 37.4Accuracy: 67.9%FID: 22.6
mIoU: 38.1FID: 15.3LPIPS: 0.519
FID: 22.4
Frechet Inception Distance: 163.4Number of Params: 28.2M
mIoU: 14.06FID: 27.8
mIoU: 13.4FID: 28.6
mIoU: 44.1FID: 17.0