ssameerr / MixNMatch

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
[Paper]

Yuheng Li, Krishna Kumar Singh, Utkarsh Ojha, Yong Jae Lee
UC Davis
In arXiv, 2019

The code and pre-trained models will be released soon.

Demo Video

Results

1. Extracting all factors from differnet real images to synthesize a new image

2. Comparison between the feature and code mode

3. Manipulating real images by varying a single factor

4. Inferring style from unseen data

Cartoon -> image	Sketch -> image

5. Converting a reference image according to a reference video

Citation

If you find this useful in your research, consider citing our work:

@inproceedings{li-arxiv2019,
  title = {MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation},
  author = {Yuheng Li and Krishna Kumar Singh and Utkarsh Ojha and Yong Jae Lee},
  booktitle = {arXiv},
  year = {2019}
}