Estimating human pose and shape from monocular images is a long-standing problem in
computer vision. Since the release of statistical body models, 3D human mesh recovery has …

Denoising diffusion models hold great promise for generating diverse and realistic human
motions. However, existing motion diffusion models largely disregard the laws of physics in …

We introduce a method for generating realistic pedestrian trajectories and full-body
animations that can be controlled to meet user-defined goals. We draw on recent advances …

Simulation has emerged as an indispensable tool for scaling and accelerating the
development of self-driving systems. A critical aspect of this is simulating realistic and …

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 …

We present ArtiGrasp, a novel method to synthesize bimanual hand-object interactions that
include grasping and articulation. This task is challenging due to the diversity of the global …

We propose a physics-based method for synthesizing dexterous hand-object interactions in
a full-body setting. While recent advancements have addressed specific facets of human …

Crafting a single, versatile physics-based controller that can breathe life into interactive
characters across a wide spectrum of scenarios represents an exciting frontier in character …

Learning-based approaches to monocular motion capture have recently shown promising
results by learning to regress in a data-driven manner. However due to the challenges in …

We present a novel method for recovering the absolute pose and shape of a human in a pre-
scanned scene given a single image. Unlike previous methods that perform sceneaware …