Papers with Code · CC BY-SA 4.0

Unsupervised Image-To-Image Translation

7 평가 기록 2 datasets

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>

논문

Adversarial Discriminative Domain Adaptation

1702.05464 2017-02-17 이 페이지의 평가 1건

Classification Accuracy: 76.0%

CyCADA: Cycle-Consistent Adversarial Domain Adaptation

1711.03213 2017-11-08 이 페이지의 평가 1건

Classification Accuracy: 90.4%

In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks

1711.09334 2017-11-26 이 페이지의 평가 1건

PSNR: 21.65

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

1703.10593 2017-03-30 이 페이지의 평가 1건

PSNR: 18.57

Unsupervised Cross-Domain Image Generation

1611.02200 2016-11-07 이 페이지의 평가 1건

Classification Accuracy: 84.4%

Unsupervised Domain Adaptation by Backpropagation

1409.7495 2014-09-26 이 페이지의 평가 1건

Classification Accuracy: 73.6%

Unsupervised Image-to-Image Translation Networks

1703.00848 2017-03-02 이 페이지의 평가 1건

PSNR: 9.42