Paul Starke

We now have new demos in AI4AnimationPy for stylized biped and quadruped locomotion control. Besides PC you can also run them in your browser or on your phone. Try it out here🎮: Web-Demo: paulstarke-ai4animationpy.hf.space GitHub: github.com/facebookresear… Video: youtube.com/watch?v=qifmLp…

@arnputz the client handles rendering, user input, and sends control inputs to the server who returns pose updates from the single cpu inference

@ps_starke on browser the infos are send to a server and model runs on the server gpu?

We now have new demos in AI4AnimationPy for stylized biped and quadruped locomotion control. Besides PC you can also run them in your browser or on your phone. Try it out here🎮: Web-Demo: paulstarke-ai4animationpy.hf.space GitHub: github.com/facebookresear… Video: youtube.com/watch?v=qifmLp…

Excited to share AI4AnimationPy, a new light-weight Python framework for data-driven character animation. We've got videos, code, models, demos, and a full documentation. GitHub: github.com/facebookresear… Full video: youtu.be/LKl7MzFENUs

Animation quality is a difficult subject that I think we've not quite got to grips with yet as a community. My latest blog post shares some of my own thoughts on the subject. My hope is it can kickstart some discussions... or at least new dance moves! theorangeduck.com/page/animation…

Super excited to see our work on codebook matching for VR motion tracking featured in the Unity 6 release! with @blacksquirrel__

Had some really good demo session at the #SIGGRAPH2024 Experience Hall today with @ps_starke to showcase our paper on Categorical Codebook Matching! Our technical paper presentation is on Thursday in the Character Control session, come join us there!

🖥️ Dive into hands-on Technical Papers demos at #SIGGRAPH2024! Join us in Exhibit Hall F from 11:15 am–1:15 pm and 3 pm–5 pm for interactive showcases of cutting-edge research. Don’t miss out on innovative projects and engaging experiences!

Want to #WalkTheDog in the metaverse? In our project at #SIGRAPH2024 with @blacksquirrel__ , Yuting Ye and @OlgaSorkineH, we develop an approach to learn a common 1D phase manifold from motion datasets across different morphologies, *without* any supervision (1/2)

What a time to be embodied! Thanks to Two Minute Papers for covering our latest work on learning realistic embodied character movements in AR/VR via Codebook Matching!

New video - New AI: This Is A Gaming Revolution! youtu.be/2zGhxnoKBWc

The code, dataset and demos for our #SIGGRAPH2024 work on generating embodied avatar movements with Codebook Matching are now available! Everything can be found on the project page, including a precompiled binary that you can play around with! github.com/sebastianstark…

@blacksquirrel__ Paper can be found here github.com/sebastianstark…

Interested in upgrading your Motion Matching system? Check out our #SIGGRAPH2024 work where we introduce *Codebook Matching* to train neural character controllers for synthesizing lifelike embodied animations in #Games and #VR! Project Page: github.com/sebastianstark…

We are excited to share our work on "Codebook Matching" for generating realistic embodied character movements in AR/VR (legs included)! Full video: youtu.be/NyLRcY0c0p4?si…

We're excited to announce the release of Inside-Out Body Tracking, the first vision-based tracking system for mapping out upper body movements with Quest 3, as well as an AI update that generates plausible leg motions for all Quest devices, Generative Legs ocul.us/3tOBpq0

I am happy to share our work on motion in-betweening with phase manifolds @SympCompAnim for producing realistic character animations from a small number of keyframes. Please meet us in LA August 4th for the presentation. - with @blacksquirrel__ Full Video: youtu.be/MbS1YcKhyyA

Check out how to teach quadrupedal robots lifelike agility to traverse diverse terrains and excel in high-intensity tasks like Chase Tag Game! 👇👇👇

Estimating a full-body pose from only the headset and controllers is ambiguous. Environment information can help resolve this. In our #SIGGRAPH2023 paper the avatar is generated from only the 3 shown coordinate frames (no cameras) + height of the environment (green dots). (1/4)👇

Our paper "Avatars Grow Legs" (CVPR 2023) is out! TL; DR: Fast Diffusion models to generate full body motions based on head and hands tracking inputs, Will release the code in a few days.

New Video - EA’s Gaming AI: Incredible Juggling Skills! youtu.be/L5KOQkZOusE #gaming

There is now a nice video tutorial that explains how to reproduce our SIGGRAPH 2022 DeepPhase research for learning a quadruped motion controller with the AI4Animation framework. Thanks to @ps_starke! Video: youtube.com/watch?v=3ASGrx… GitHub: github.com/sebastianstark…