Combining Variational Autoencoders & Generative Adversarial Networks to Improve Image Quality

Generative Adversarial Networks(GAN) are trained to generate images from random noise vectors, but often these images turn out poorly due to any of several reasons such as model collapse, lack of proper training data, lack of training, etc. To combat this issue this paper, makes use of a Variational Autoencoder(VAE) . The VAE is trained on a combination of the training & generated data, after this the VAE can be used to map images generated by the GAN to better versions of it. (This is similar to Denoising, but with few variations in the image). In addition to improving quality the proposed model is shown to work better than normal WGAN’s on sparse datasets with higher variety, in equal number of training epochs