AVAE: Adversarial Variational Auto Encoder

TL;DR

This paper introduces AVAE, a novel framework combining Variational Auto Encoders and Generative Adversarial Networks to produce high-quality, realistic images while maintaining the benefits of VAEs, addressing their limitations.

Contribution

The paper proposes a new hybrid model that integrates VAE and GAN to improve image realism and latent space representation.

Findings

Produces images of GAN-quality with VAE benefits

Addresses mode collapse and latent space issues

Evaluated on five datasets with positive results

Abstract

Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN). GANs can produce realistic images, but they suffer from mode collapse and do not provide simple ways to get the latent representation of an image. On the other hand, VAEs do not have these problems, but they often generate images less realistic than GANs. In this article, we explain that this lack of realism is partially due to a common underestimation of the natural image manifold dimensionality. To solve this issue we introduce a new framework that combines VAE and GAN in a novel and complementary way to produce an auto-encoding model that keeps VAEs properties while generating images of GAN-quality. We evaluate our approach both qualitatively and quantitatively on five image datasets.