Open Source Data and Tools for Generative Animation - Introducing M-body.ai - Webinar Recording and Documentation

Webinar Recording and Documentation

Open Source Data and Tools for Generative Animation – Introducing M-body.ai Webinar Recording and Documentation

We are thrilled to announce that the recording and presentation of our recent webinar on generative animation are now available!

Event Highlights

During the webinar, our panel of experts delved into various aspects of the project including:

  • The project goals, deliverables and team
  • The human motion dataset with the multimodal datastreams that comprise of: skeletal body animation (including hands, fingers and head), spoken audio for each seperate agent, timed transcript of spoken audio, raw facial performance capture, reference video and topologically consistent body geometry
  • Capture methodology
  • ML research challenges, sample models and evaluation of the metrics and dataset
  • Software tools: development challenges, goals, integration approaches and components
  • Design around the user intention and toolbox.
  • Licences
  • How and why to engage with the project

About M-body.ai

M-body.ai is an applied research project. Powered by a collaboration of four research centers, it’s led by Sheridan College’s Screen Industries Research and Training Centre (SIRT), including Durham College’s Mixed Reality Capture Studio (MRC) and AI Hub, Centre de développement et de recherche en intelligence numérique (CDRIN) of Cégep de Matane, and Le Laboratoire en innovation ouverte (LLio) of Cégep de Rivière-du-Loup. M-body.ai is funded by the National Sciences and Engineering Research Council of Canada (NSERC).

What We’re Creating

All outputs of the project will be open-source, free, and commercially usable. They will include:

  • A dataset of multi-modal, multi-agent interactions: To support training generative ML models with diverse, high-quality data.
  • Generative animation tools: To improve the efficiency of creating humanoid animations.
  • Open-source software systems: To streamline the integration of generative character performance models into industry-standard content creation tools.

Why Watch the Recording?

Whether you are a researcher or developer interested in generative animation or a production studio or animator looking to integrate Generative AI into your workflows, this webinar offers insights and knowledge.

So, don’t miss out on this opportunity to enhance your understanding of the project with the full recording of the webinar.

Don’t hesitate to give us feedback about the webinar here. You can also click here to access the Slidedeck.

Soon, we will also put online a version with French subtitles.

How to engage?

Join us by testing, or even co-developing with us. Fill out this form to get involved! We look forward to your feedback and are excited to continue this journey with you. Stay tuned for more updates and upcoming events!

Got questions? We have answers! Don’t hesitate to send us an email.