SGGAN

A PyTorch implementation of SGGAN proposed in Segmentation guided image-to-image translation with adversarial networks (FG 2019) (arXiv preprint version).

by Songyao Jiang, Zhiqiang Tao and Yun Fu

News

• Processed segmentations for CelebA dataset is released.
• Our journal extention of this work has been published in TIP: Geometrically Editable Face Image Translation With Adversarial Networksl

Segmentation data

Preprocessed segmentation data for CelebA can be downloaded via Google Drive

Citation

If you find this repo useful in your research, please cite the following paper:

@inproceedings{jiang2019segmentation,
  title={Segmentation guided image-to-image translation with adversarial networks},
  author={Jiang, Songyao and Tao, Zhiqiang and Fu, Yun},
  booktitle={2019 14th IEEE International Conference on Automatic Face \& Gesture Recognition (FG 2019)},
  pages={1--7},
  year={2019},
  organization={IEEE}
}

@article{jiang2021geometrically,
  title={Geometrically Editable Face Image Translation With Adversarial Networks},
  author={Jiang, Songyao and Tao, Zhiqiang and Fu, Yun},
  journal={IEEE Transactions on Image Processing},
  volume={30},
  pages={2771--2783},
  year={2021},
  publisher={IEEE}
}

License

This project is released under the MIT License.

Reference

https://github.com/yunjey/stargan