Our research uses Computer Vision to learn digital humans that can perceive, learn, and act in virtual 3D worlds. This involves capturing the shape, appearance, and motion of real people as well as their interactions with each other and the 3D scene using monocular video. We leverage this to learn generative models of people and their behavior and evaluate these models by synthesizing realistic looking humans behaving in virtual worlds.
This work combines Computer Vision, Machine Learning, and Computer Graphics.
Director
Admin Team
Department Highlights
GraspXL: Generating Grasping Motions for Diverse Objects at Scale

MonoHair: High-Fidelity Hair Modeling from a Monocular Video

SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis

Generative Proxemics: A Prior for 3D Social Interaction from Images

HIT: Estimating Internal Human Implicit Tissues from the Body Surface

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

TeCH: Text-guided Reconstruction of Lifelike Clothed Humans

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

FLARE: Fast learning of Animatable and Relightable Mesh Avatars

From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans
