Welcome to this webinar arranged by WARA Media and Language where Gustav Eje Henter, WASP assistant professor at the Division of Speech, Music and Hearing at KTH Royal Institute of Technology, will talk about MoGlow, a new, award-winning deep-learning architecture that leverages normalising flows.
If you wish to attend, please register using the link below.
Abstract
Data-driven character animation holds great promise for enhancing realism and creativity in games, film, virtual avatars and social robots. However, due to the high bar on visual quality, most existing AI animation solutions focus narrowly on a specific task, and do not generalise to different motion types.
This talk makes the case that 1) machine learning now has advanced far enough that strong, task-agnostic motion models are possible, and that 2) these models should be probabilistic in nature, to accommodate the great diversity in how behaviours can be realised. We present MoGlow, a new, award-winning deep-learning architecture that leverages normalising flows and satisfies our two desired criteria. Experiments show that MoGlow is competitive with the state-of-the-art in locomotion generation for both humans and dogs.
For a longer introduction showing our models in action, please see the following video: MoGlow: Probabilistic and controllable motion synthesis using normalising flows
Bio Gustav Eje Henter
Gustav Eje Henter is a WASP assistant professor in machine learning at the Division of Speech, Music and Hearing at KTH. His main research interests are probabilistic modelling and deep learning for data-generation tasks, especially speech and motion/animation synthesis.
He has an MSc and a PhD from KTH, followed by post-docs in speech synthesis at the Centre for Speech Technology Research at the University of Edinburgh, UK, and in Prof. Junichi Yamagishi’s lab at the National Institute of Informatics, Tokyo, Japan, before returning to KTH in 2018.