Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies

TL;DR

This paper introduces a unified 3D deformation model called 'Adam' for markerless, simultaneous tracking of facial expressions, hand gestures, and body movements in everyday clothing, enabling comprehensive human motion capture.

Contribution

The paper presents a novel integrated deformation model that combines facial, hand, and body tracking into a seamless system, improving realism and applicability in natural settings.

Findings

Successfully captures full-body, face, and hand movements simultaneously.

Creates a calibrated model 'Adam' that reflects real-world clothing and hair.

Demonstrates total motion tracking in social group scenarios.

Abstract

We present a unified deformation model for the markerless capture of multiple scales of human movement, including facial expressions, body motion, and hand gestures. An initial model is generated by locally stitching together models of the individual parts of the human body, which we refer to as the "Frankenstein" model. This model enables the full expression of part movements, including face and hands by a single seamless model. Using a large-scale capture of people wearing everyday clothes, we optimize the Frankenstein model to create "Adam". Adam is a calibrated model that shares the same skeleton hierarchy as the initial model but can express hair and clothing geometry, making it directly usable for fitting people as they normally appear in everyday life. Finally, we demonstrate the use of these models for total motion tracking, simultaneously capturing the large-scale body movements and the subtle face and hand motion of a social group of people.