DeeperForensics-1.0
DeeperForensics-1.0 copied to clipboard
How did you generate deepfakes for frames where no faces were detected in the original video in FaceForensics++?
Thanks for the great dataset. While creating a deepfake dataset, I came up with a question. When generating deepfakes, sometimes faces are not detected in the original video frames. How did you handle this situation in the frames of the original FaceForensics++ video?