When you can't detect a face

Rudrabha / Lip2Wav

This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"

MIT License

692 stars 152 forks source link

Closed MontaEllis closed 4 years ago

MontaEllis commented 4 years ago

Hi, I'm trying to refactor your code in Pytorch. And I wonder why your model can generate mel even when the model can't detect a face? Thanks a lot!

prajwalkr commented 4 years ago

Could you please explain? We do not understand the question. Also, what do you feed into the 3D-CNN if you do not have a face crop?

prajwalkr commented 4 years ago

Closing due to inactivity. Please re-open again, if necessary.