Bored? Of course you are, it’s Monday. So why not use this little AI-powered tool to turn a photo of your face into a 3D model, then idly spin it round, pondering exactly how and when super-intelligent robots will liquidate your body and replace you with a perfect 3D-printed simulacra.
Okay, so that’s probably not what’s going to happen here, as this widget is the result of some normal research from The University of Nottingham and Kingston University in the UK. (Although, that’s exactly what super-intelligent robots would want you to think.)
As the researchers note in a recent paper describing their work, “3D face reconstruction is a fundamental computer vision problem of extraordinary difficulty.” You usually need multiple pictures of the same face from different angles in order to map every contour. But, by feeding a bunch of photographs and corresponding 3D models into a neural network, the researchers were able to teach an AI system how to quickly extrapolate the shape of a face from a single photo.
Look, here’s a 3D David Bowie:
And a 3D mask:
Being able to create 3D models of faces like this could have all sorts of applications in the digital world: from 3D avatars for video games, to warping your face in an augmented reality video, to VR social media. And, as AI makes it easier to turn all sorts of 2D photos into 3D objects (not just faces) it’ll be easy to create virtual environments of all sorts.
Try it for yourself here.