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.

Information and registration

View all events
We use cookies to personalise content and ads, to provide social media features and to analyse our traffic. We also share information about your use of our site with our social media, advertising and analytics partners. View more
Cookies settings
Accept
Privacy & Cookie policy
Privacy & Cookies policy
Cookie name Active
The WASP website wasp-sweden.org uses cookies. Cookies are small text files that are stored on a visitor’s computer and can be used to follow the visitor’s actions on the website. There are two types of cookie:
  • permanent cookies, which remain on a visitor’s computer for a certain, pre-determined duration,
  • session cookies, which are stored temporarily in the computer memory during the period under which a visitor views the website. Session cookies disappear when the visitor closes the web browser.
Permanent cookies are used to store any personal settings that are used. If you do not want cookies to be used, you can switch them off in the security settings of the web browser. It is also possible to set the security of the web browser such that the computer asks you each time a website wants to store a cookie on your computer. The web browser can also delete previously stored cookies: the help function for the web browser contains more information about this. The Swedish Post and Telecom Authority is the supervisory authority in this field. It provides further information about cookies on its website, www.pts.se.
Save settings
Cookies settings