3D Face Reconstruction from a Single Image

A group of AI experts from The University of Nottingham and Kingston University managed to create a new method by which two-dimensional images of faces can be converted into 3D using machine learning.

The researchers trained a convolutional neural-network to perform the task by feeding it tons of data on people’s faces. From there it figured out how to guess what a new face looks like from an previously unseen pic, including parts that it can’t see in the photograph.

Upload your own face here. Source code here.

Like it? Share with your friends!




Get something good in your email

Get something good in your email

Tired of getting emails that all try to sell you something? Why not subscribe to our daily GIF email? We send this out only once per day if there has been new activity on the site. You can unsubscribe anytime and we do not share your information or try and sell you something.

You have Successfully Subscribed!

Pin It on Pinterest