DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection

Liming Jiang
Ren Li
Wayne Wu
Chen Qian
Chen Change Loy

Nanyang Technological University
SenseTime Research




In this paper, we present our on-going effort of constructing a large-scale benchmark, DeeperForensics-1.0, for face forgery detection. Our benchmark 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. We believe this dataset will contribute to real-world face forgery detection research.




Demo




Paper

DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection

Liming Jiang, Ren Li, Wayne Wu, Chen Qian, Chen Change Loy

To appear in CVPR, 2020.
[PDF]
[BibTex]


Downloads


DeeperForensics-1.0 Dataset

Code


Comparison




Method (DF-VAE)


We also propose a new learning-based many-to-many face swapping method, DeepFake Variational Auto-Encoder (DF-VAE). DF-VAE improves scalability, style matching, and temporal continuity to ensure face swapping quality. In training, we reconstruct the source and target faces in blue and orange arrows, respectively, by extracting landmarks and constructing an unpaired sample as the condition. Optical flow differences are minimized after reconstruction to improve temporal continuity. In inference, we swap the latent codes and get the reenacted face in green arrows. Subsequent MAdaIN module fuses the reenacted face and the original background resulting in the swapped face.



Visualizations



Extensive Data Collection



Several Face Manipulation Results



Many-to-Many (Three-to-Three) Face Swapping by a Single Model



Diverse Perturbations in Real World



Acknowledgements

We gratefully acknowledge the exceptional help from Hao Zhu and Keqiang Sun for source data collection and coordination.