The metaverse is a nascent concept that envisions a virtual universe, a collaborative space
where individuals can interact, create, and participate in a wide range of activities. Privacy in …

The growing interest in the Metaverse has generated momentum for members of academia
and industry to innovate toward realizing the Metaverse world. The Metaverse is a unique …

The Metaverse has the potential to form the next pervasive computing archetype that can
transform many aspects of work and life at a societal level. Despite the many forecasted …

With the recent surge in popularity of AR/VR applications, realistic and accurate control of
3D full-body avatars has become a highly demanded feature. A particular challenge is that …

Abstract We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality
human motion generation. Current state-of-the-art generative diffusion models have …

Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose,
a versatile framework to model plausible 3D human poses for various applications. At the …

Estimating 3D human motion from an egocentric video sequence plays a critical role in
human behavior understanding and has various applications in VR/AR. However, naively …

Controllable human motion synthesis is essential for applications in AR/VR, gaming and
embodied AI. Existing methods often focus solely on either language or full trajectory control …

We present EMDB, the Electromagnetic Database of Global 3D Human Pose and Shape in
the Wild. EMDB is a novel dataset that contains high-quality 3D SMPL pose and shape …

We present a physics-based humanoid controller that achieves high-fidelity motion imitation
and fault-tolerant behavior in the presence of noisy input (eg pose estimates from video or …