Unsupervised Image-To-Image Translation

2 benchmarks124 papers

Unsupervised image-to-image translation is the task of doing image-to-image translation without ground truth image-to-image pairings.

<span style="color:grey; opacity: 0.6">( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )</span>

Benchmarks

Unsupervised Image-To-Image Translation on Freiburg Forest Dataset

PSNR

Unsupervised Image-To-Image Translation on SVNH-to-MNIST

Classification Accuracy