Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation

04/27/2018
by   Salman H. Khan, et al.
0

Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a new approach to alleviate this problem in the VAE based generative models. Our model simultaneously learns to match the data, reconstruction loss and the latent distributions of real and fake images to improve the quality of generated samples. To compute the loss distributions, we introduce an auto-encoder based discriminator model which allows an adversarial learning procedure. The discriminator in our model also provides perceptual guidance to the VAE by matching the learned similarity metric of the real and fake samples in the latent space. To stabilize the overall training process, our model uses an error feedback approach to maintain the equilibrium between competing networks in the model. Our experiments show that the generated samples from our proposed model exhibit a diverse set of attributes and facial expressions and scale up to high-resolution images very well.

READ FULL TEXT

page 6

page 7

page 8

research
06/28/2022

AS-IntroVAE: Adversarial Similarity Distance Makes Robust IntroVAE

Recently, introspective models like IntroVAE and S-IntroVAE have excelle...
research
05/20/2020

Tessellated Wasserstein Auto-Encoders

Non-adversarial generative models such as variational auto-encoder (VAE)...
research
05/19/2017

Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generation

Variational auto-encoder (VAE) is a powerful unsupervised learning frame...
research
04/06/2022

Statistical Model Criticism of Variational Auto-Encoders

We propose a framework for the statistical evaluation of variational aut...
research
02/28/2017

Towards Deeper Understanding of Variational Autoencoding Models

We propose a new family of optimization criteria for variational auto-en...
research
04/30/2019

The Level Weighted Structural Similarity Loss: A Step Away from the MSE

The Mean Square Error (MSE) has shown its strength when applied in deep ...
research
12/05/2016

Authoring image decompositions with generative models

We show how to extend traditional intrinsic image decompositions to inco...

Please sign up or login with your details

Forgot password? Click here to reset