WHY?

VAE can learn useful representation while GAN can sample sharp images.

WHAT?

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. image

Algorithm is as follows.

image

So?

IVAE achieved realistic quality reconstruction and sample from CelebA, CelebA-HQ, and LSUN Bedroom. Also the representations learned from IVAE showed meaningful latent manifold.

Critic

Amazing image quality!

Huang, Huaibo, et al. “IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis.” arXiv preprint arXiv:1807.06358 (2018).