Generative Adversarial Networks for Image Synthesis and Translation

Abstract: Recent generative models are adept at solving Image domain transfer problems, i.e., they learn to transform an image based on a set of training examples. These are usually based on generative adversarial networks (GANs), and can be supervised or unsupervised as well as unimodal or multimodal. I will present a number of our recent methods in this space that can be used to translate, for instance, a label map to a realistic street image, a day time street image to a night time street image, a dog to different cat breeds, and many more.

Bio: Jan is VP of Learning and Perception Research at NVIDIA, where he leads the Learning & Perception Research team. He is working predominantly on computer vision problems (from low-level vision through geometric vision to high-level vision), as well as machine learning problems (including generative models and efficient deep learning). Before joining NVIDIA in 2013, Jan was a tenured faculty member at University College London. He holds a BSc in Computer Science from the University of Erlangen-Nürnberg (1999), an MMath from the University of Waterloo (1999), received his PhD from the Max-Planck-Institut für Informatik (2003), and worked as a post-doctoral researcher at the Massachusetts Institute of Technology (2003-2006).