search

bbaaii / HFA-GP

Official implementation of High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors
57 stars 5 forks source link

Cross-person renactment #2

Open oijoijcoiejoijce opened 1 year ago

oijoijcoiejoijce commented 1 year ago

Great work! How would you suggest doing cross-person renactment (i.e. face, expression and pose of person A into video of person B)

ChikaYan commented 1 year ago

I have similiar questions. I have tried training on one identity and then running cross-reenactment on the other identy via RGB image signals. However the result is really poor: hfa-question

Above are source, drive and result respectively.

May I ask if this is expected? I.e, cross-reenactment via RGB signals does give quite bad quality? I noticed that in the paper there is only audio-driven/3DMM coefficients driven reenactment.

Many thanks.