joonson/syncnet_python

Is it possible for multiple face tracking?

Closed this issue · 2 comments

I notice that the function track_shot could track only one random face. What if I have multiple faces in a shot? Is it possible for multiple face tracking?

I believe the pipeline works for multiple faces in a shot. Have you tried running and visualizing the output?

The pipeline does works for multiple faces. And I notice that the pycrop file store all detected face tracks and its corresponding audios.