FaceForensics++ is a forensics dataset consisting of 1000 original video sequences that have been manipulated with four automated face manipulation methods: Deepfakes, Face2Face, FaceSwap and NeuralTextures The data has been sourced from 977 youtube videos and all videos contain a trackable mostly frontal face without occlusions which enables automated tampering methods to generate realistic forgeries.
322 PAPERS • 2 BENCHMARKS
VideoForensicsHQ is a benchmark dataset for face video forgery detection, providing high quality visual manipulations. It is one of the first face video manipulation benchmark sets that also contains audio and thus complements existing datasets along a new challenging dimension. VideoForensicsHQ contains 1,737 videos of speaking faces (44% male, 56% female), with 8 different emotions, most of them of “HD” resolution. The videos amount to 1,666,816 frames.
2 PAPERS • NO BENCHMARKS YET
A high-resolution version of VGGFace2 for academic face editing purposes. This project uses GFPGAN for image restoration and insightface for data preprocessing (crop and align).
1 PAPER • NO BENCHMARKS YET
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 The source videos are collected on 100 paid and consented actors from 26 countries, and the manipulated videos are generated by a newly proposed many-to-many end-to-end face swapping method, DF-VAE. 7
22 PAPERS • NO BENCHMARKS YET
WildDeepfake is a dataset for real-world deepfakes detection which consists of 7,314 face sequences extracted from 707 deepfake videos that are collected completely from the internet.
35 PAPERS • NO BENCHMARKS YET
…The head poses are very diverse and often hard to be detected by a CNN-based face detector.
112 PAPERS • 8 BENCHMARKS