This project was inspired by a cool blog post.
See it live here
Using a pre-trained model (PoseNet) using ml5js we estimate eye-position, and then use ThreeJS to render the screen from this eye position.
In future, I would like to estimate head depth, but this would involve using a more complicated model.
Lucy model adapted from Princeton Suggestive Contour Gallery , originally from Stanford 3D scanning respository.