1. [Publications](/index.php/publications)
2. Unsupervised Image-to-Image Translation Networks
 
 # Unsupervised Image-to-Image Translation Networks

  ![](/sites/default/files/styles/wide/public/publications/street_scene_for_press.png?itok=Yb3NOSRo)

 Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions. To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs. We compare the proposed framework with competing approaches and present high quality image translation results on various challenging unsupervised image translation tasks, including street scene image translation, animal image translation, and face image translation. We also apply the proposed framework to domain adaptation and achieve state-of-the-art performance on benchmark datasets.



 ## Authors



[Ming-Yu Liu](/index.php/person/ming-yu-liu)

[Thomas Breuel](/index.php/person/thomas-breuel)

[Jan Kautz](/index.php/person/jan-kautz)

 

 

 ## Publication Date



Monday, December 4, 2017

 

 ## Published in



[NIPS](https://nips.cc/)

 

 ## Research Area



[Computer Vision](/index.php/research-area/computer-vision)

[Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence)

 

 

 ## External Links



[Code](https://github.com/mingyuliutw/UNIT)

[Snowy to summery image translation result video 01](https://youtu.be/9VC0c3pndbI)

[Snowy to summery image translation result video 02](https://youtu.be/eUBiiBS1mj0)

[Day to night image translation result video 01 ](https://youtu.be/Z_Rxf0TfBJE)

[Day to night image translation result video 02](https://youtu.be/mmj3iRIQw1k)

[Image translation between 5 dog breeds](https://youtu.be/3a6Jc7PabB4)

[Image translation between 6 cat species](https://youtu.be/Bwq7BmQ1Vbc)

[Additional image translation results](https://photos.app.goo.gl/5x7oIifLh2BVJemb2)

[arXiv paper link](https://arxiv.org/abs/1703.00848)

 

 

 ## Copyright



Copyright (C) 2017 NVIDIA Corporation. All rights reserved. Licensed under the CC BY-NC-ND 4.0 license