TUM AI Lecture Series - AI-Generated Digital Humans (Hao Li)

1 Просмотры
Abstract: In a post-pandemic world, virtual meetings and events are going to stay and the need for immersive technologies using virtual avatars has never been more obvious. I will highlight three areas where digital humans will play a key role, including virtual communication, immersive content, and next generation human-machine interaction. While the vfx and gaming industry is pushing the envelope for hyperrealistic virtual humans, the technology is still designed for professionals. I will show the latest avatar digitization technology from Pinscreen, making the creation of digital humans accessible to anyone, as well as our real-time hybrid neural face rendering technology paGAN, allowing us to cross the uncanny valley using an AI approach. I will showcase various real-world applications, from fashion avatars to virtual companions. Furthermore, I will present a Star Wars hologram-like system for volumetric human teleportation, allowing us to digitize our entire body in 3D using a single webcam. Our 3D deep learning approach is realtime and can generate a complete 3D model of a clothed subject while only a single 2D view is available.

Bio: Hao Li is CEO and Co-Founder of Pinscreen, a startup that builds cutting edge AI-driven virtual avatar technologies. He is also a Distinguished Fellow of the Computer Vision Group at UC Berkeley. Before that, he was an Associate Professor of Computer Science at the University of Southern California, as well as the director of the Vision and Graphics Lab at the USC Institute for Creative Technologies. Hao's work in Computer Graphics and Computer Vision focuses on digitizing humans and capturing their performances for immersive communication, telepresence in virtual worlds, and entertainment. His research involves the development of novel deep learning, data-driven, and geometry processing algorithms. He is known for his seminal work in avatar creation, facial animation, hair digitization, dynamic shape processing, as well as his recent efforts in preventing the spread of malicious deep fakes. He was previously a visiting professor at Weta Digital, a research lead at Industrial Light & Magic / Lucasfilm, and a postdoctoral fellow at Columbia and Princeton Universities. He was named top 35 innovator under 35 by MIT Technology Review in 2013 and won the Office of Naval Research (ONR) Young Investigator Award in 2018. Hao was named named to the DARPA ISAT Study Group in 2019 and won the ACM SIGGRAPH Real-Time Live! “Best in Show” award in 2020.

TUM AI Lecture Series previous lectures:
- Learning with energy-based models (Thomas Pock):

- Sensible Algorithms for Learning from Geometric Data (Justin Solomon):
Комментариев нет.