Title: Adversarial Latent Autoencoders
About This Project:
In this project, Stanislav Pidhorskyi, Donald Adjeroh, Gianfranco Doretto introduced an autoencoder that tackles these issues jointly, which we call Adversarial Latent Autoencoder (ALAE). It is a general architecture that can leverage recent improvements on GAN training procedures. We designed two autoencoders: one based on a MLP encoder, and another based on a StyleGAN generator, which we call StyleALAE. If you want to add something to this project or create something like this, Go through the demo and code link given below.
Code, Demo, And Other Details: Adversarial Latent Autoencoders