On the estimation of the Wasserstein distance in generative models

no code implementations • 2 Oct 2019 • Thomas Pinetz, Daniel Soukup, Thomas Pock

Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets.

Impact of the latent space on the ability of GANs to fit the distribution

no code implementations • 25 Sep 2019 • Thomas Pinetz, Daniel Soukup, Thomas Pock

The goal of generative models is to model the underlying data distribution of a sample based dataset.