Ming Yu Liu (NVIDIA)
Image and Video Synthesis with Conditional GANs
Presentation recorded August 21, 2020
Abstract: A series of works on using the conditional GAN framework for controllable image and video synthesis will be covered in the talk. I will start by providing an overview of a different image and video synthesis settings and their challenges. I will then discuss how we address these challenges using the conditional GAN framework. I will showcase their applications and how they could impact the content creation industry. The talk will be concluded with a discussion on the current obstacles and future research directions.
Bio: Ming-Yu Liu is a Distinguished Research Scientist and Manager at NVIDIA Research. Before joining NVIDIA in 2016, he was a Principal Research Scientist at Mitsubishi Electric Research Labs (MERL). He received his Ph.D. from the Department of Electrical and Computer Engineering at the University of Maryland College Park under the supervision of Prof. Rama Chellappa in 2012. He won the R&D 100 Award by R&D Magazine for his robotic bin picking work in 2014. In SIGGRAPH 2019, he won the Best in Show Award and Audience Choice Award in the Real-Time Live track for his GauGAN work. His GauGAN work also won the Best of What's New Award by the Popular Science Magazine in 2019. His research interest is on generative image modeling. His goal is to enable machines human-like imagination capability.