FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
This addresses the need for reliable fake video detectors in applications like social media, where manipulation detection is challenging due to compression and low resolution, though it is incremental as it focuses on dataset creation rather than novel detection methods.
The authors tackled the problem of detecting manipulated face videos by introducing FaceForensics, a large-scale dataset of about half a million edited images from over 1000 videos, which exceeds existing datasets by at least an order of magnitude, and they established benchmarks for classification and segmentation tasks across various compression levels.
With recent advances in computer vision and graphics, it is now possible to generate videos with extremely realistic synthetic faces, even in real time. Countless applications are possible, some of which raise a legitimate alarm, calling for reliable detectors of fake videos. In fact, distinguishing between original and manipulated video can be a challenge for humans and computers alike, especially when the videos are compressed or have low resolution, as it often happens on social networks. Research on the detection of face manipulations has been seriously hampered by the lack of adequate datasets. To this end, we introduce a novel face manipulation dataset of about half a million edited images (from over 1000 videos). The manipulations have been generated with a state-of-the-art face editing approach. It exceeds all existing video manipulation datasets by at least an order of magnitude. Using our new dataset, we introduce benchmarks for classical image forensic tasks, including classification and segmentation, considering videos compressed at various quality levels. In addition, we introduce a benchmark evaluation for creating indistinguishable forgeries with known ground truth; for instance with generative refinement models.