Yes, that IS a video of the Mona Lisa talking.
How? Artificial Intelligence. More specifically - "Deep Fake" technology engineered by Samsung in Moscow.
Fake videos are nothing new... We see them every day on social media. Most of the time we don't even know they're fakes unless someone points it out to us.
I hate to throw around the term "Fake News"... But all of Donald Trump's fears may be becoming a reality soon.
Previously, most deep fake software required a very large number of images of a particular person’s face in order to map that face onto a video. But Samsung's new software can create fairly convincing fake videos from just a few images of a person. It can potentially even work from a single image.
To demonstrate the new software's abilities, Samsung shared a video showing fun applications, in which celebreties came alive from a single image. There's a clip of Mona Lisa at the end of the video, animated to seemingly come alive and talk.
In terms of misuse of their product, the author of the research papers from the software says: “We realize that our technology can have a negative use for the so-called ‘deepfake’ videos. However, it is important to realize that Hollywood has been making fake videos (aka ‘special effects’) for a century, and deep networks with similar capabilities have been available for the past several years.”
The ability to doctor videos in this way is similar to the way we can doctor photos in photoshop already, but as the software becomes readily available, it's important to remember that just because you've seen it in a video, doesn't mean it's real!
Check out the somewhat creepy video for yourself below: