Official Pytorch implementation of Effective De-identification Generative Adversarial Network for Face Anonymization published at ACM International Conference on Multimedia. 2021
Diverse versions results with DEIDGAN by varying the input
In this repository, we propose an approach, termed as DEIDGAN, for face anonymization. Our approach consists of two steps. First, we anonymize the input face to obfuscate its original identity. Then, we use our designed de-identification generator to synthesize an anonymized face.
@inproceedings{kuang2021effective,
title={Effective De-identification Generative Adversarial Network for Face Anonymization},
author={Kuang, Zhenzhong and Liu, Huigui and Yu, Jun and Tian, Aikui and Wang, Lei and Fan, Jianping and Babaguchi, Noboru},
booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
pages={3182--3191},
year={2021}
}