ICCV 2017 Tutorial on GANs

Venice, Italy

22 October 2017

Generative adversarial networks (GANs) have been at the forefront of research on generative models in the last couple of years. GANs have been used for image generation, inpaiting, photo synthesis from text, image editing and many other applications, often leading to state of the art results.

The aim of this tutorial is to provide a broad overview of generative adversarial networks, starting with introductory topics and continuing with an exploration of state of the art GAN models, models using adversarial loss as well as theoretical considerations regarding GANs.

For more details on the speakers and topics, including slides from speakers please see our schedule page.

For an example of the power of generative adversarial networks, see the below samples from StackGAN: