This is a forensics dataset that uses four automatic face-changing algorithms: Face2Face, FaceSwap, DeepFakes, and NeuralTextures to process 1,000 real video sequences. The data comes from 977 YouTube videos, all of which contain a trackable and mostly unobstructed frontal face, making the generated faces as realistic as possible. Example image:

Citation

@inproceedings{roessler2019faceforensicspp,
author = {Andreas R\"ossler and Davide Cozzolino and Luisa Verdoliva and Christian Riess and Justus Thies and Matthias Nie{\ss}ner},
title = {Face{F}orensics++: Learning to Detect Manipulated Facial Images},
booktitle= {International Conference on Computer Vision (ICCV)},
year = {2019}
}