lucidrains / pi-GAN-pytorch

Implementation of π-GAN, for 3d-aware image synthesis, in Pytorch
MIT License
116 stars 15 forks source link

Question in FilmSiren #9

Closed sunwoo76 closed 2 years ago

sunwoo76 commented 2 years ago

Hello.

Your paper is very impressive. However I have a question.

The original siren module is designed very theoretically with some equations and statistical theory as below: siren .

If the input "x" is modulated with the value gamma and beta, the "var(x)" would change. The CLT condition would be not fulfilled in consequence of modulated siren(FilmSiren).

Could you explain why does the FilmSiren work well a little please?

Thank you :)