VAE can learn useful representation while GAN can sample sharp images.
Introspective Variational Autoencoder(IVAE) combines the advantage of VAE and GAN to make a model to learn useful representation and output sharp images. IVAE uses encoder to introspectively estimate the generated samples and the training data as a discriminator.
Algorithm is as follows.
IVAE achieved realistic quality reconstruction and sample from CelebA, CelebA-HQ, and LSUN Bedroom. Also the representations learned from IVAE showed meaningful latent manifold.
Amazing image quality!
Subscribe via RSS