mIoU: 74.4
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: 70.0
mIoU: 62.0
mIoU: 64.1
mIoU: 75.6
mIoU: 70.3
mIoU: 61.2
mIoU: 60.8
mIoU: 56.1
mIoU: 58.6
mIoU: 68.3
mIoU: 62.7
mIoU: 56.6
mIoU: 55.0
mIoU: 57.3
mIoU: 59.7
mIoU: 73.8
mIoU: 59.7
mIoU: 58.2
mIoU: 54.2
mIoU: 69.4
mIoU: 57.5
mIoU: 53.8
mIoU: 63.9