Researchers at Samsung AI center, have found a way to turn a single photo into a talking head using an algorithm that captures “landmark” facial features then maps them onto a photo to bring it to life.
Ai (artificial intelligence) can now make a fake video of you with just one photo.
This sequence of the movie Harry Potter, Prisoner of Azbakan were pictures are moving, reminders you of anything?
The researchers at Samsung’s AI Centre have found a way to create “living portraits ”
How Does it Work?
The algorithm recognizes “landmark” facial features like the shape of the faces, eyes mouth and more. Then it maps these features onto a photo to bring it to “life”. The more images that are fed into the program the more accurate the result will be.
Researchers from Samsung’s AI Center and Skolkovo Institute of Science and Technology in Moscow, released an explainer on how they’ve trained neural networks to transform still portraits into lifelike videos, calling them “talking head models.” One example turned Leonardo da Vinci’s Mona Lisa into a breathing, moving human.
It’s fascinating to see the world’s most famous subject come to life, especially considering the painting’s much-debated and mysterious history. Dropping her static, signature smile for once, she looks quite contemporary. But it’s also jarring to consider how fast AI imaging is advancing, and what that means for our already contested media landscape.
Some are concerned that this technology could be used to spread misinformation.
The other's are hopping they get this software soon in their hands.
Watch the video for more:-