https://github.com/NVlabs/MUNIT

Multimodal Unsupervised Image-to-Image Translation
https://github.com/NVlabs/MUNIT

deep-learning gan image-translation munit pix2pix

Last synced: 3 months ago
JSON representation

Multimodal Unsupervised Image-to-Image Translation

• Host: GitHub
• URL: https://github.com/NVlabs/MUNIT
• Owner: NVlabs
• License: other
• Created: 2018-03-30T21:56:14.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2022-09-20T12:23:52.000Z (about 2 years ago)
• Last Synced: 2024-05-22T16:32:51.931Z (6 months ago)
• Topics: deep-learning, gan, image-translation, munit, pix2pix
• Language: Python
• Homepage:
• Size: 5.97 MB
• Stars: 2,620
• Watchers: 74
• Forks: 480
• Open Issues: 64
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

• awesome-list - MUNIT - Multimodal Unsupervised Image-to-Image Translation. (Computer Vision / Image / Video Generation)
• awesome-ARTificial - MUNIT - Multimodal UNsupervised Image-to-image Translation (Uncategorized / Uncategorized)

README

        
**The code base is no longer maintained.**

**Please check here for an improved implementation of MUNIT: https://github.com/NVlabs/imaginaire/tree/master/projects/munit**

[![License CC BY-NC-SA 4.0](https://img.shields.io/badge/license-CC4.0-blue.svg)](https://raw.githubusercontent.com/NVIDIA/FastPhotoStyle/master/LICENSE.md)

![Python 2.7](https://img.shields.io/badge/python-2.7-green.svg)

![Python 3.6](https://img.shields.io/badge/python-3.6-green.svg)

## MUNIT: Multimodal UNsupervised Image-to-image Translation

### License

Copyright (C) 2018 NVIDIA Corporation.  All rights reserved.

Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode). 

For commercial use, please consult [NVIDIA Research Inquiries](https://www.nvidia.com/en-us/research/inquiries/).

### Code usage

Please check out the [user manual page](USAGE.md).

### Paper

[Xun Huang](http://www.cs.cornell.edu/~xhuang/), [Ming-Yu Liu](http://mingyuliu.net/), [Serge Belongie](https://vision.cornell.edu/se3/people/serge-belongie/), [Jan Kautz](http://jankautz.com/), "[Multimodal Unsupervised Image-to-Image Translation](https://arxiv.org/abs/1804.04732)", ECCV 2018

### Results Video

[![](results/video.jpg)](https://youtu.be/ab64TWzWn40)

### Edges to Shoes/handbags Translation

![](results/edges2shoes_handbags.jpg)

### Animal Image Translation

![](results/animal.jpg)

### Street Scene Translation

![](results/street.jpg)

### Yosemite Summer to Winter Translation (HD)

![](results/summer2winter_yosemite.jpg)

### Example-guided Image Translation

![](results/example_guided.jpg)

### Other Implementations

[MUNIT-Tensorflow](https://github.com/taki0112/MUNIT-Tensorflow) by [Junho Kim](https://github.com/taki0112)

[MUNIT-keras](https://github.com/shaoanlu/MUNIT-keras) by [shaoanlu](https://github.com/shaoanlu)

### Citation

If you find this code useful for your research, please cite our paper:

```

@inproceedings{huang2018munit,

  title={Multimodal Unsupervised Image-to-image Translation},

  author={Huang, Xun and Liu, Ming-Yu and Belongie, Serge and Kautz, Jan},

  booktitle={ECCV},

  year={2018}

}

```