search

yuval-alaluf / SAM

Official Implementation for "Only a Matter of Style: Age Transformation Using a Style-Based Regression Model" (SIGGRAPH 2021) https://arxiv.org/abs/2102.02754
https://yuval-alaluf.github.io/SAM/
MIT License
632 stars 151 forks source link

Applying old face effects #19

Closed MetiCodePrivateLimited closed 3 years ago

MetiCodePrivateLimited commented 3 years ago

I want to make my selfie into old face effects as the current configuration change my face into someone else old face. How can I make my face into real old face just like "FaceApp" android app.

Do I need to train my own model? If yes, from where can I get free faces on which I will train my own comprehensive model for male, female and children as well?

yuval-alaluf commented 3 years ago

As mentioned in the paper, preserving identity is a challenge when modeling human aging. There is a tradeoff between modeling meaningful changes in age and preserving identity. You can completely preserve identity, but not model meaningful changes. On the other hand, you can model meaningful changes, but hurt the identity of the output. With SAM I try to balance the two. If you find the results to be unsatisfactory, you can try training a model on a different dataset. As I mentioned in your other issues, I do not know of other age datasets of high resolution so you're a bit on your own here. I am also a bit unfamiliar with the results of the FaceApp.