Anatomically-Constrained Local Deformation Model for Monocular Face Capture

 

We propose a local deformation model composed of many small subspaces spatially distributed over the face.

July 11, 2016
ACM SIGGRAPH 2016

 

 

 

Authors

Chenglei Wu (ETH Zurich)

Derek Bradley (Disney Research)

Markus Gross (Disney Research/ETH Zurich)

Thabo Beeler (Disney Research)

Anatomically-Constrained Local Deformation Model for Monocular Face Capture

Abstract

In contrast to approaches that leverage texture synthesis for creating decorative surface patterns, our method relies on user-defined spline curves as central design primitives. More specifically, we build on the physically-inspired metaphor of an embedded elastic curve that can move on a smooth surface, deform, and connect with other curves. We formalize this idea as a globally coupled energy-minimization problem, discretized with piece-wise linear curves that are optimized in the parametric space of a smooth surface. Building on this technical core, we propose a set of interactive design and editing tools that we demonstrate on manually-created layouts and semi-automated deformable packings. In order to prevent excessive compliance, we furthermore propose a structural analysis tool that uses eigenanalysis to identify potentially large deformations between geodesically-close curves and guide the user in strengthening the corresponding regions. We used our approach to create a variety of designs in simulation, validated with a set of 3D-printed physical prototypes.

Copyright Notice