You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For face swapping, it is something like "copy and paste" in our framework, which relies on a face segmentor and we deform the source face so that it can fit to the target face. The GAN loss during training mainly optimizes the deformation field instead of making realistic face swapping (e.g. face boundary).
I have tested some data collected by myself.
the results are terrible.
could you provide some test data showed in your readme?
The text was updated successfully, but these errors were encountered: