DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
This provides a more challenging benchmark for researchers in face forgery detection, though it is incremental as it builds on existing dataset efforts.
They tackled the problem of detecting face forgeries by creating DeeperForensics-1.0, the largest dataset with 60,000 videos and 17.6 million frames, 10 times larger than existing ones, and validated its quality through user studies.
We present our on-going effort of constructing a large-scale benchmark for face forgery detection. The first version of this benchmark, DeeperForensics-1.0, represents the largest face forgery detection dataset by far, with 60,000 videos constituted by a total of 17.6 million frames, 10 times larger than existing datasets of the same kind. Extensive real-world perturbations are applied to obtain a more challenging benchmark of larger scale and higher diversity. All source videos in DeeperForensics-1.0 are carefully collected, and fake videos are generated by a newly proposed end-to-end face swapping framework. The quality of generated videos outperforms those in existing datasets, validated by user studies. The benchmark features a hidden test set, which contains manipulated videos achieving high deceptive scores in human evaluations. We further contribute a comprehensive study that evaluates five representative detection baselines and make a thorough analysis of different settings.