Hacker News Reader

Comment by gnicholas | Hacker News Reader

It showed someone participating in a group video call. But it only showed what the other people (who were not wearing headsets) look like. What does the Vision Pro user look like? Does it just use animoji or something?

EDIT: sounds like they render a realistic animated image of you, if I caught that correctly?

View on HN

They've got a interior facing camera, they could make you a pair of floating eyeballs!

Kidding, but also not, I imagine they make use of that camera for this somehow.

I'm suspecting they'll ask users to enroll/login with camera for IPD correction, then make a figurative Live2D model using that picture, interior camera and lip sync.

Edit: and yep, your head is modeled and a doppelganger of you will show in calls.

They're talking about this now. Sounds basically like this, except 3d. They also have lips (using downwards facing cameras I guess).

I wonder how this will work without the ability to capture full facial expressions. Can they extrapolate from the features they can see, to fill in the gaps of what they can't see? Or will tone of voice be sufficient to let people know when you're happy or upset?

This could be the next generation of "tone gets lost in text".

From what they showed, it will be a reallistic-looking 3D avatar of yourself. It's quite into uncanny valley territory but it will likely improve over time. What they demoed looks a bit like a blurry deepfake.

Suspiciously accurate! As they just explained on the stream, this is exactly how it will work.

Your edit is correct. I was just going to reply. Your stream seems to be ahead of mine :(

Probably because I'm just down the road from Cupertino. That's how the internet works, right?

Here in Hillsborough. Your stream seemed to be a lot more than 5ms ahead.

I think I was in a 4 or 5k stream. Whatever apples page delivers when on a 5k monitor I guess.

I thought that was funny as well. I suppose this is where the new "poster" feature comes in? They'll just see pre-recorded looped video of you?

You use the front LIDAR to scan the depth map of your face while the actual cameras take pictures.

Then they construct a virtual avatar out of that.

Reply on news.ycombinator.com