iFakeFaceDB is face image dataset for the study of synthetic face manipulation detection, comprising about 87,000 synthetic face images generated by the Style-GAN model [1] and transformed with the GANprintR approach. All images were aligned and resized to the size of 224 x 224.
The official implementation of the method used to generate this dataset can be found at https://github.com/joaocneves/gan_fingerprint_removal
The use of this software is RESTRICTED to non-commercial research and educational purposes.
@misc{1911.05351,
title={{GANprintR: Improved Fakes and Evaluation of the State-of-the-Art in Face Manipulation Detection}},
author={João C. Neves and Ruben Tolosana and Ruben Vera-Rodriguez and Vasco Lopes and Hugo Proença and Julian Fierrez},
year={2019},
eprint = {arXiv:1911.05351},
}
[1] Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4401-4410).