PSNR: 12.191SSIM: 0.278
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: 63.1FID: 52.1Accuracy: 93.5
mIoU: 44.8
mIoU: 41.3
mIoU: 60.8
mIoU: 49.9
mIoU: 55.2
mIoU: 58.6
mIoU: 68.3
mIoU: 41.7
mIoU: 62.7
mIoU: 73.6FID: 44.1
mIoU: 62.0
Per-pixel Accuracy: 82.5%mIoU: 64.2FID: 59.5
mIoU: 59.7
Per-pixel Accuracy: 81.4%mIoU: 58.3FID: 95
Per-pixel Accuracy: 82.3%mIoU: 65.5FID: 54.3LPIPS: 0.073
PSNR: 10.769SSIM: 0.1757
Per-pixel Accuracy: 77.1%mIoU: 52.4FID: 104.7
mIoU: 57.5
Per-pixel Accuracy: 81.9%mIoU: 62.3FID: 71.8
Per-pixel Accuracy: 82.5%mIoU: 66FID: 54.2
mIoU: 63.9
mIoU: 76.3FID: 38.2
mIoU: 47.0
mIoU: 41.3
mIoU: 69.3FID: 47.7LPIPS: 0.275