I implemented several parametric modeling techniques with my homebrew geometry / math libraries in C++ and rendered in UE4. #### Solid of Revolution Essentially you take a curve (perhaps a b-spline,
Advances in sequential modeling via deep learning allows procedurally generated names for RPG characters that belong in Tolkienesque worlds. I used pretty much the simplest sequential model - an RNN,
I led development of a social VR co-located framework we used to teach Ken Perlin's graduate Computer Graphics students to work in VR. Every group was able to create their own 1 to 1 "meta(verse)" roo
I've been thinking a lot lately about networking and how we use it for our co-located immersive experiences. What are the pressing questions as one designs such a system for shared experiences like t
The recent explosion of deep learning has demonstrated its awesome power, but data driven machine learning isn't the end of the story. Machine learning is only one piece of the puzzle, in the futur
Zhu Wang and I made a real-time distributed co-located demo for a Rokoko contest (we were runner ups!) and a video with the help of our labmates at the NYU Future Reality Lab. Check it out the user st
Now that we have room-scale co-located tracking with no external sensors, thanks to the Quest, and Connor DeFanti's calibration sche
For a project during my masters degree, we implemented the paper Learning to Generate Chairs by Dosovitskiy et. al. in PyTorch. The only implementation a
wherein I generate a distribution of fungi
