If you're wondering why you're seeing Barak Obama's picture next to a post titled "create your face in 3D", you are not alone. I was killing my time surfing online when i came across this headline "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression". Quite a boring sciency sounding title for what actually is a nifty little project. Converts a photograph of your face into a 3D model.
The researchers achieve this by training a Convolutional Neural Network (CNN) on an appropriate dataset consisting of 2D images and 3D facial models or scans. Do you think this could be useful? Anyone think of 3D avatars? But with a little help from AI could photographing people in 3D could be that simple!
Why not try it here.
