SDGAN: Semantic-aware De-identification Generative Adversarial Networks for Identity Anonymization
Our research has experimented on various angles, occlusion, facial expressions, gender, ages, skin colors etc.
To the best of our knowledge, our research has been tested under the most diverse conditions.
Front Face Images
Side Face Images
Occlusion Face Images
** Now, we are preparing to share the code. **
## Installation
Please download the code:
To use our code, first download the repository:
````
git clone https://github.com/kimhyeongbok/SDGAN.git
````
To install the dependencies:
````
pip install -r requirements.txt
````
## Citation
If you find this code useful, please consider citing the following paper:
````
@article{kim2022SDGAN,
title={Semantic-aware deidentification generative adversarial networks for identity anonymization},
author={Hyeongbok Kim, Zhiqi Pang, Lingling Zhao, Xiaohong Su and Jin Suk Lee},
journal={Multimedia Tools and Applications},
year={2022}
}
````