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

Jun-Yan Zhu*    Taesung Park*    Phillip Isola    Alexei A. Efros

UC Berkeley

In ICCV 2017

[Paper] [Code (Torch)] [Code (PyTorch)]

Abstract

Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G: X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F: Y → X and introduce a cycle consistency loss to push F(G(X)) ≈ X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.

paper thumbnail

Paper

arxiv 1703.10593, 2017.

Citation

Jun-Yan Zhu*, Taesung Park*, Phillip Isola, and Alexei A. Efros. "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks", in IEEE International Conference on Computer Vision (ICCV), 2017.
(* indicates equal contributions) Bibtex

Code: [Torch] [PyTorch]


Other Implementations

[Tensorflow] (by Harry Yang), [Tensorflow] (by Archit Rathore), [Tensorflow] (by Van Huy), [Tensorflow] (by Xiaowei Hu)
[Tensorflow-simple] (by Zhenliang He), [Chainer] (by Yanghua Jin), [Minimal PyTorch] (by yunjey), [Mxnet] (by Ldpe2G), [lasagne/keras] (by tjwei)


Expository Articles and Videos

Two minute papers

Karoly Zsolnai-Feher made the above as part of his very cool "Two minute papers" series.

Understanding and Implementing CycleGAN

Nice explanation by Hardik Bansal and Archit Rathore, with Tensorflow code documentation.

Creative Applications of CycleGAN

Researchers, developers and artists have tried our code on various image manipulation and artistic creatiion tasks. Here we highlight a few of the many compelling examples. Search CycleGAN in Twitter for more applications.

Converting Monet into Thomas Kinkade

What if Claude Monet had lived to see the rise of Americana pastoral kitsch in the style of Thomas Kinkade? And what if he resorted to it to support himself in his old age? Using CycleGAN, our great David Fouhey finally realized the dream of Claude Monet revisiting his cherished work in light of Thomas Kinkade, the self-stylized painter of light.

Resurrecting Ancient Cities

Jack Clark used our code to convert ancient maps of Babylon, Jerusalem and London into modern Google Maps and satellite views.

Animal Transfiguration

Tatsuya Hatanaka trained our method to translate black bears to pandas. See more examples and download the models at the website. Matt Powell performed transfiguration between different species of birds

Portrait to Dollface

Mario Klingemann used our code to translate portraits into dollface. See how the characters in Game of Thrones look like in the doll world.

Face ↔ Ramen

Takuya Kato performed a magical and hilarious Face ↔ Ramen translation with CycleGAN. Check out more results here

Colorizing legacy photographs

Mario Klingemann trained our method to turn legacy black and white photos into color versions.

Cats ↔ Dogs

itok_msi produced cats ↔ dogs CycleGAN results with a local+global discriminator and a smaller cycle loss.

Popular Press


Applications in our Paper

Monet Paintings → Photos

Mapping Monet paintings to landscape photographs from Flickr:
[Best results], [Random training set results], [Random test set results]

 

Collection Style Transfer

Transferring input images into artistic styles of Monet, Van Gogh, Ukiyo-e, and Cezanne.
[Results on the author's personal photos]
[Random training set results], [Random test set results]

 

Object Transfiguration

Object transfiguration between horses and zebras:
[Best results], [Random training set results], [Random test set results]
Object transfiguration between apples and oranges:
[Best results], [Random training set results], [Random test set results]

Horse Video to Zebra Video

 

Season Transfer

Transferring seasons of Yosemite in the Flickr photos:
[Best results], [Random training set results], [Random test set results]

 

Photo Enhancement

iPhone photos → DSLR photos: generating photos with shallower depth of field.
[Best Results], [Random training set results], [Random test set results]

 

Experiments and comparisons

Various Applications

Failure Cases

failure

Our model does not work well when a test image looks unusual compared to training images, as shown in the left figure. See more typical failure cases [here]. On translation tasks that involve color and texture changes, like many of those reported above, the method often succeeds. We have also explored tasks that require geometric changes, with little success. For example, on the task of dog ↔ cat transfiguration, the learned translation degenerates to making minimal changes to the input. Handling more varied and extreme transformations, especially geometric changes, is an important problem for future work. We also observe a lingering gap between the results achievable with paired training data and those achieved by our unpaired method. In some cases, this gap may be very hard -- or even impossible,-- to close: for example, our method sometimes permutes the labels for tree and building in the output of the cityscapes photos → labels task. To resolve this ambiguity may require some form of weak semantic supervision. Integrating weak or semi-supervised data may lead to substantially more powerful translators, still at a fraction of the annotation cost of the fully-supervised systems.





Related Work


Acknowledgement

We thank Aaron Hertzmann, Shiry Ginosar, Deepak Pathak, Bryan Russell, Eli Shechtman, Richard Zhang, and Tinghui Zhou for many helpful comments. This work was supported in part by NSF SMA-1514512, NSF IIS-1633310, a Google Research Award, Intel Corp, and hardware donations from NVIDIA. JYZ is supported by the Facebook Graduate Fellowship and TP is supported by the Samsung Scholarship. The photographs used in style transfer were taken by AE, mostly in France.