Face Identity Disentanglement via Latent Space Mapping

ID-disentanglement-Pytorch

Pytorch implementation of the paper Face Identity Disentanglement via Latent Space Mapping for both training and evaluation, with StyleGAN 2.

Changes from original paper

• instead of using a Discriminator loss for the mapper. We have used several other losses such as:
  • LPIPS Loss (The Unreasonable Effectiveness of Deep Features as a Perceptual Metric, Zhang el al, 2018)
  • MSE Loss
  • Different ID Loss
  • Different landmark detector
• The reason for those changes resides in the fact that the training procedure with Discriminator is often
  hard and does not converge. We have found that replacing the Discriminator with LPIPS and MSE losses
  we can achieve the same result. Nevertheless, our code supports training with a discriminator which can be
  activated using the configuration.
• The other changes are due to

   

   

   

  To finish reading, please visit source site