https://github.com/compvis/content-style-disentangled-st

Content and Style Disentanglement for Artistic Style Transfer [ICCV19]
https://github.com/compvis/content-style-disentangled-st

Last synced: 19 days ago
JSON representation

Content and Style Disentanglement for Artistic Style Transfer [ICCV19]

• Host: GitHub
• URL: https://github.com/compvis/content-style-disentangled-st
• Owner: CompVis
• Created: 2019-08-11T21:00:56.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2021-02-22T12:49:34.000Z (almost 5 years ago)
• Last Synced: 2025-02-15T07:46:57.297Z (12 months ago)
• Homepage: https://compvis.github.io/content-style-disentangled-ST
• Size: 51.5 MB
• Stars: 96
• Watchers: 16
• Forks: 16
• Open Issues: 5
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Content and Style Disentanglement for Artistic Style Transfer

***Dmytro Kotovenko, Artsiom Sanakoyeu, Sabine Lang, Björn Ommer*,  ICCV 2019**

[**Project page**](https://compvis.github.io/content-style-disentangled-ST/) | 

[**Paper**](https://compvis.github.io/content-style-disentangled-ST/paper.pdf) | 

[**Supplementary Material**](https://compvis.github.io/content-style-disentangled-ST/Content_and_Style_Disentanglement_for_Artistic_Style_Transfer_ICCV19_supplementary.pdf) |

[**Code**](https://github.com/CompVis/content-style-disentangled-ST/tree/dev_subm_1)

![pipeline](https://github.com/CompVis/content-style-disentangled-ST/blob/gh-pages/images/pipeline_5x_v3_cropped.jpg "Method pipeline")

**Preliminary version of the source code is located in branch [dev_subm_1](https://github.com/CompVis/content-style-disentangled-ST/tree/dev_subm_1).** 

### Video Results   

[**Teaser video**](https://www.youtube.com/embed/KN_WTcQBUsU)    

[Full playlist](https://www.youtube.com/playlist?list=PLPXplX5Y1SzGOxo22bqZjV1V-_LgcmLnT)

### Style Interpolations

Click on GIF for Hi-Res version.  

Input             |  Cezanne to van Gogh

:-------------------------:|:-------------------------:

![](https://compvis.github.io/content-style-disentangled-ST/images/gif4.jpg) | [![Foo](https://compvis.github.io/content-style-disentangled-ST/images/gif4_hires_optimized_500px.gif "Hi-Res GIF")](https://compvis.github.io/content-style-disentangled-ST/images/gif4_hires_optimized.gif)

Input             |  Cezanne to van Gogh

:-------------------------:|:-------------------------:

![](https://compvis.github.io/content-style-disentangled-ST/images/gif3_500px.jpg)  |  [![Foo](https://compvis.github.io/content-style-disentangled-ST/images/gif3_hires_optimized_500px.gif "Hi-Res GIF")](https://compvis.github.io/content-style-disentangled-ST/images/gif3_hires_optimized.gif)

Input             |  Cezanne to van Gogh

:-------------------------:|:-------------------------:

![](https://compvis.github.io/content-style-disentangled-ST/images/gif7.jpg)  |  [![Foo](https://compvis.github.io/content-style-disentangled-ST/images/gif7_hires_optimized_500px.gif "Hi-Res GIF")](https://compvis.github.io/content-style-disentangled-ST/images/gif7_hires_optimized.gif)

## Our previous work on Style Transfer

- [A Content Transformation Block For Image Style Transfer (CVPR19)](https://github.com/CompVis/content-targeted-style-transfer)

- [A Style-Aware Content Loss for Real-time HD Style Transfer (ECCV18)](https://github.com/CompVis/adaptive-style-transfer)

## Reference

If you use our work in your research, please cite us using the following BibTeX entry.

```

@conference{kotovenko2019iccv,

  title={Content and Style Disentanglement for Artistic Style Transfer},

  author={Kotovenko, Dmytro, adn Sanakoyeu, Artsiom, and Lang, Sabine, and Ommer, Bj\"orn},

  booktitle={Proceedings of the International Conference on Computer Vision (ICCV)},

  year={2019}

}

```