Quote:
Originally Posted by HastenDan
Plucked from latent space. Wowza
Couldn't really understand your post. May want to mention that it's partly interpolated images using neural networks. Figure is from page 6 of this paper:
https://arxiv.org/pdf/1703.10717.pdf
Boundary Equilibrium Generative Adversarial Networks
David Berthelot, Tom Schumm, Luke Metz
Google, Inc.
Abstract
We propose a new equilibrium enforcing method paired with a loss derived from
the Wasserstein distance for training auto-encoder based Generative Adversarial
Networks. This method balances the generator and discriminator during training.
Additionally, it provides a new approximate convergence measure, fast and stable
training and high visual quality. We also derive a way of controlling the trade-off
between image diversity and visual quality. We focus on the image generation
task, setting a new milestone in visual quality, even at higher resolutions. This is
achieved while using a relatively simple model architecture and a standard training
procedure.
Last edited by simplicitus; 04-03-2017 at 03:32 AM.
Reason: "Enhance"