Body Detection & Person Segmentation Simultaneously?

Hey there,

so there is a thread also on forums.developer.apple.com about this, but maybe we can get some additional insights here.

Many people are wondering whether we're able to get (People) Segmentation and Pose information at the same time.

E.g. a use case, quoting developer from apple forums:

(Use case: a person moves among virtual objects, and those objects react to approximated collisions with the user's body. Body Detection used to generate approximate collision for the user's body, and Person Segmentation used to enforce the sense of the user moving between objects.)

If any of the developers from Unity Labs directly could give us more insights on this, that would be amazing.

thanks

 

Somebody achieved it here: https://twitter.com/mechpil0t/status/1148150238206578688

How was it done?

EDIT: The dev said je's just using poses for that example