Comment by cyode

They explain at 1:52:25 of the keynote.

Callers without Vision Pro show up on calls like normal. Vision Pro wearers are portrayed by a 3D representation of them wihtout the headset on.

> This was one of the most difficult challenges we faced in building Apple Vision Pro. There's no video conferencing camera looking at you, and even if there were, you're wearing something over your eyes. Using our most advanced ML techniques, we created a novel solution.

> After a quick enrollment process using the front sensors on Vision Pro, the system uses an advanced encoder-decoder neural network, to create your digital Persona. This network was trained on a diverse group of thousands of individuals. It delivers a natural representation which dynamically mathces your facial and hand movement. With your Persona, you can communicate with your a billion FaceTime-capable devices. When viewed by someone in another Vision Pro, your Persona has volume and depth not possible in traditional video.