Paolo Andreini (DIISM, University of Siena)

Nov 14, 2018 – 11:00 AM

DIISM, Artificial Intelligence laboratory (room 201), Siena SI

Description

In this seminar a new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) will be presented. Conditional GANs have enabled a variety of applications, but the results are often limited to low-resolution and still far from realistic. In the presented work, 2048 × 1024 visually appealing images are generated, with a novel adversarial loss, as well as a new multi-scale generator and discriminator architectures.