search

mchong6 / JoJoGAN

Official PyTorch repo for JoJoGAN: One Shot Face Stylization
MIT License
1.42k stars 206 forks source link

Perceptual loss: LPIPS vs. StyleGAN Discriminator #22

Closed matanby closed 2 years ago

matanby commented 2 years ago

Hi!

Thanks for sharing this awesome work :-)

I'm wondering on the difference in perceptual image quality when using the LPIPS model (as stated in the paper) vs. the StyleGAN discriminator (as used in the updated collab notebook) for the perceptual loss. In your experience, what kind of difference does using the StyleGAN discriminator have on the image quality, when compared to using LPIPS?

mchong6 commented 2 years ago

Hi, the paper should be updated on arxiv with some comparison. But generally lpips captures less details and has some downsampling artifacts.

matanby commented 2 years ago

I've just noticed the updated paper, and read through the relevant section. Thanks for the answer!