Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks

no code implementations • CVPR 2018 • Alexander Sage, Eirikur Agustsson, Radu Timofte, Luc van Gool

We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training.

Clustering

Optimal transport maps for distribution preserving operations on latent spaces of Generative Models

no code implementations • ICLR 2018 • Eirikur Agustsson, Alexander Sage, Radu Timofte, Luc van Gool

Generative models such as Variational Auto Encoders (VAEs) and Generative Adversarial Networks (GANs) are typically trained for a fixed prior distribution in the latent space, such as uniform or Gaussian.