You're viewing a single thread.
106
comments
AI has to advance to a point it can reliably ID someone using the camera despite different models and potential obstructions.
Hopefully by that point, it can also be used to generate a fake video file of "someone paying attention" to output to a virtual camera :)
It would be the same technology, because both use cases would require AI to have built an accurate model of what human faces look like
106
comments