Mindplex Podcast Episode 29: Ryan Sternlicht — The AI 3D Revolution
Learn about the amazing advances in AI-enhanced 3D model rendering that were showcased at this year’s GDC conference in San Francisco.
Join us this Friday, April 12th at 12pm PST/7pm UTC with special guest Ryan Sternlicht, fresh back from GDC to tell us all about the current revolution in AI 3D rendering and your host Lisa Rein.
We will cover all of the amazing AI-enhanced advances for capturing and rendering 3D models for: printed wearables, virtual clothing, in-world avatars, virtual worlds, real-time facial capture, real-time physics, and more.
Join Mindplex Podcast LIVE — Friday, April 12th at 12 pm PST/7 pm UTC.
Episode 29: The AI 3D Revolution
AI has literally revolutionized 3D scanning, from markerless motion capture to high-quality avatars generated from text and images. You can now use AI to create 3D scans using only your cell phone, and these scans can be used to make beautiful 3D printed objects and professional quality wearables, and in-world avatars.
Deemos Tech’s Hyperhuman ChatAvatar is literally generating hyper realistic avatars in a few minutes — using their massive 3D scan database. They can do the full body, but their most impressive feature is their photorealistic heads. These models are photorealistic to a level that basically very few companies can achieve, even when those other companies are doing things using non AI traditional workflows.
You can even use AI to re-render your old scans into superior new high quality 3D models. All of these new features combined are making 3D printing more efficient and accessible to everyone.
Another huge advance that AI has enabled is real-time markerless motion capture — as demonstrated by AR51. “Markerless motion capture” is camera-based motion capture without wearing a suit or special equipment — and its integration with AI processing is what enables the real-time 3D capture. Plus it’s able to run on regular high-end computers — as opposed to specialized machines or servers requiring a massive number of GPUs.
As Ryan explains:
It is amazing how quickly this stuff runs and how realistic the rigging can be at this point. It’s getting incredibly realistic, incredibly fast. You can put things in 3D, in XR, in real-time. Some recent common uses of real time motion capture are virtual avatar based concerts, and XR games.
I was literally being motion-tracked the instant I walked into their booth. Like they had it running in real time. I walked in the booth and it would be tracking me pretty much perfectly.
Ryan will also cover these AI Advances:
- NeRF’s, 3D Gaussian Splatting, and SMERF advances for 3D world representation and AI models for photogrammetry.
- Real-time error correction during the printing process that enables faster 3D printing.
- Image to 3D full physics clothing simulation for video games and in-world models.
- Real-time facial capture.
- Real-time physics.
- Avatar generation directly from text and images.
About Ryan Sternlicht
Ryan Sternlicht is a San Francisco-raised educator, researcher, advisor, and maker, who has advised a number of startups in the fields of AR, VR, AI, neurotech, and 3D manufacturing.
As a maker, he has volunteered or advised a number of makerspaces and hackerspaces, as well as numerous technical non-profit organizations in California and upstate New York.
While in the Bay Area, he volunteers and teaches at Noisebridge Hackerspace, and staffs a large number of film festivals and conventions, such as Aaron Swartz Day, Offkai Expo, Maker Faire, and Open Sauce. He also works at Alamo Drafthouse New Mission, and helps teach game development at CCSF.
About Mindplex
The Mindplex Podcast team invites you to join them as they contemplate and learn about this fascinating world. They look forward to meeting you so you can help each other understand the true nature of all the challenges involved as we work together to create a Benevolent Singularity.
The Mindplex Podcast and Mindplex Magazine — are both part of the Mindplex decentralized media platform spin-off powered by SingularityNet
We invite you to check out the Mindplex website, set up a profile, and perhaps even contribute to the magazine.
Follow us:
- Visit Mindplex Magazine
- Join our Telegram
- Join our Mindplex Social
- Join our Discord
- Follow us on Twitter, LinkedIn
- Like us on Facebook
