Samsung has brought the Mona Lisa to life using artificial intelligence and a single photo of the famous Leonardo Da Vinci painting.
A video of the endeavor shows the model and noblewoman with the enigmatic smile moving her head, eyes and mouth.
The algorithms work best when a variety of photos of a subject are used, taken from different angles, but they can also be effective with just one picture. They were developed by a team from the Samsung AI Center and the Skolkovo Institute of Science and Technology.
Samsung’s algorithms were trained on a public database of thousands of images of celebrities featured on YouTube. The artificial intelligence system then maps facial features and movement onto a face to bring it to life.
The team behind this new AI development has also made models of Salvador Dali and Marilyn Monroe and outlined their work in a paper, Few-Shot Adversarial Learning of Realistic Neural Talking Head Models.
This latest iteration of so-called deep fake technology received a mixed reaction. While some praised the ingenuity and could see numerous applications such as more realistic personal avatars in VR games, others are concerned. They worry about the potential for misuse such as creating fake versions of political figures to spread false messages.
Samsung’s researchers acknowledge the technology could be misused but also point out the many positives such as allowing relatives of grieving people to create avatars of them after they die.
For more information on the technology click here to read the Samsung paper.