The program uses artificial intelligence to produce a full 3D model of your face – and it’s free to use.
A team of experts from Kingston University and the University of Nottingham has created a program that maps a 3D version of a person’s face from a single photograph.
The so-called 3D selfie is formed using artificial intelligence that recognizes features in a flat image and reconfigures them into a 3D model.
Although it was developed in a computer science lab, it’s now been put on the internet for anyone to try out.
So far, more than 430,000 users have created 3D selfies of themselves.
“What’s really impressive about this technique is how it has made the process of creating a 3D facial model so much simpler,” said Dr. Vasileios Argyriou, from Kingston University’s Faculty of Science, Engineering, and Computing.
“Going from 2D to 3D has previously involved a number of stages that we’ve been able to bypass – we don’t have to select specific features, or use morphable models.
“We give the system a certain amount of data and it then learns in a similar way to how we process seemingly unconnected information – allowing it to draw conclusions for what a flat image of a person’s face would look like in three dimensions.”
The team used a database of over 80,000 2D images alongside corresponding 3D models to train the computer into recognizing key features.
Future uses of the technology include detecting faces in crowds or creating personal avatars in video games.