This morning, Mark Zuckerberg announced that PyTorch is moving to a new, independent #PyTorchFoundation as part of the #LinuxFoundation umbrella. Learn what’s next for one of the leading platforms for #AI research and production applications. bit.ly/3RY99HW

This paper shows some of our research at Meta Reality Labs in reconstructing a user's pose from only the sensors of the Quest headset using Reinforcement Learning. authors: with Jungdam Won and Yuting Ye paper: arxiv.org/abs/2209.09391 video: youtu.be/CkTHsz6Ldas 1/4👇

Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model abs: arxiv.org/abs/2304.08577 project page: dulucas.github.io/agrol/

Our CVPR2023 paper is finally out on arxiv🤩 this is a joint work with Artsiom Sanakoyeu Albert Pumarola Ali Thabet Robin KIPS Sebastian Starke during my internship at Meta. Amazing team and fantastic experience!!! Stay tuned for the code.

We have released the code and weights for our #CVPR2023 paper "Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model"! code: github.com/facebookresear… abs: arxiv.org/abs/2304.08577 project: dulucas.github.io/agrol/ The demo is below:

Happy to share our new paper on hair reconstruction that will appear at #ICCV2023, congrats to Vanessa Sklyarova and colleagues! We produce a detailed and personalized strand-based hairstyle from the monocular video. Project page: samsunglabs.github.io/NeuralHaircut More details in the thread 🧵

"HMD-NeMo: Online 3D Avatar Motion Generation from Sparse Observations" will be presented at #ICCV2023. Please come and meet us (Room "Foyer Sud" - 013, on Thursday 10:30AM) Link to paper: openaccess.thecvf.com/content/ICCV20… Together with Fatemeh Saleh, David, Pashmina, and Darren Cosker

Excited to share that the launch of our "Generative Legs" was announced last week at Meta Connect. This ML based technology allows to generate a realistic full body motion given the available tracking signal of the VR headset without additional sensors, in real time.

Excited to share 🔥OmniControl🔥 for incorporating 💭flexible spatial control signals💭 into a text-conditioned human motion generation. The generated motions are realistic, coherent, and consistent with the spatial constraints. -Project page: neu-vi.github.io/omnicontrol/

The CoreAI team at Meta Reality Labs is hiring 2024 interns to work on 3D Generative AI. Joins us to explore (& publish) new methods for texture and shape synthesis and stylization. Feel free to message me if you have any questions or apply directly! metacareers.com/jobs/711711463…

We’re excited for you to start experimenting with all of the new tools and capabilities in our v60 release. Check out what’s new across Haptics, MR Utility Kit, Movement SDK, and more, and learn how these updates can help you accelerate your development: ocul.us/3TPa01J

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

Our Generative Legs technology is now available for all Quest devices !

Hand tracking side-by-side comparison 🙌 Top: Apple Vision Pro Bottom: Meta Quest 3

Introducing Cryptic Cabinet, a new open source mixed reality showcase built with Presence Platform helps turn any room into a unique gameplay experience. ocul.us/3UM9imb