Deepfakes use machine learning techniques to create images and videos in which real people appear to do things they never did, or to create imaginary people who never existed at all. The technique involves merging images of different people to create the “fake.” I’m using a similar technique to merge images of the same people over time. Video frames are merged into a still to create a snapshot of the person in time that isn’t always as you recalled them. I call this technique, “DeepReals.”
DeepReals (2019) is work in progress. The first in the series is:
The First Three Minutes
Every frame from the first three minutes of Christine Blasey Ford’s and Brett Kavanaugh’s testimony before the Senate Judiciary Committee, September 2018.