XR

Q&A for Autonomous Digital Humans and Artificial Intelligence

Author(s)/Presenter(s):
Doug Roble, Digital Domain, United States of America
Darren Hendler, Digital Domain, United States of America

Abstract: In the spring of 2019 we presented a real-time, photorealistic version of Doug that mimicked what the real Doug was doing at the annual TED Conference. Since then, we’ve been working on making him look even better, make it easier to create high quality characters like him and to give him the ability to interact with people on his own. Our goal was to create something that looked impeccable and could be driven by a client’s chatbot. In doing this, we had to build an entire autonomous framework to handle all aspects of how a digital human interacts with the world. Self-driving cars? Ha! We’re talking about self-driving people! Machine learning requires data and we’ve spent considerable effort on our performance capture pipeline. This has had a huge impact on our VFX capabilities and has also made creating realistic, autonomous characters easier. We will discuss many aspects of what we’ve learned as we created this new technology.

---

Q&A for A Helping Hand: How can digital humans improve lives and accessibility

Author(s)/Presenter(s):
Mike Seymour, fxguide, Motus Lab USYD

Abstract: Mike will discuss the development of high-end digital human, and how this is merging with the developments in Neural Rendering. In particular, he will explain the profound ways that such digital humans can help people with a specific focus on Health and the work he and his team along with key international collaborators are doing into using photorealistic individualised CGI digital humans to improve the lives & accessibility of young stroke survivors.

---

Q&A for How to create your own photo-realistic avatar

Author(s)/Presenter(s):
Hao Li, Pinscreen, Inc., United States of America

Abstract: As we are moving toward a future where humans are seamlessly interacting with human-like virtual agents, existing solutions are either difficult or expensive to produce and often suffer from the Uncanny Valley effect. I will showcase how we overcome these challenges through our latest technological advancements at Pinscreen. I will showcase an end-to-end cloud-based solution of a fully autonomous and photoreal avatar, as well as present our latest methods to make the digitization and personalization of avatar accessible to consumers. I will give a live and unscripted demonstration of our avatar and illustrate a few real use cases from web-based virtual assistant, hologram-based virtual hosts, to virtual fashion influencers.

---

Q&A for Digital humans are back! Panel Discussion

Author(s)/Presenter(s):
Christophe Hery, Facebook Reality Labs, United States of America
Mike Seymour, fxguide, Motus Lab USYD
Doug Roble, Digital Domain
Darren Hendler, Digital Domain, Canada
Hao Li, Pinscreen, United States of America

Abstract: Following the success of Tokyo 2018, Digital Humans are back in Siggraph Asia. And this time, they have a clear mission. In the age of covid and social distancing, these avatars and clones have to entertain us, assist us and help us communicate. After all, relatable discussions are what we, Real Humans, long for. Even more so, when isolation is forced upon us. We have invited researchers who will show the next iterations of virtual companions. These pioneers in the field of telepresence and autonomous agents, as well as visual effects and VR/AR practitioners, are not only presenting their work and approaches, but they will expand on the ethical aspects involved and how they envision a bright future for meaningful interactions with these Digital Humans.

---

Back