← ArchivePaper2011
Rigid Stabilization of Facial Expressions
Thabo Beeler, Fabian Hahn, Derek Bradley, Bernd Bickel, Paul Beardsley, Craig Gotsman, Robert Sumner, Markus Gross
Rigid motion stabilization for facial performance capture, separating head pose from expression motion for improved downstream processing.
Abstract
Facial scanning has become the industry-standard approach for creating digital doubles in movies and video games. This involves capturing an actor while they perform different expressions that span their range of facial motion. Unfortunately, the scans typically contain a superposition of the desired expression on top of un-wanted rigid head movement. In order to extract true expression deformations, it is essential to factor out the rigid head movement for each expression, a process referred to as rigid stabilization . In order to achieve production-quality in industry, face stabilization is usually performed through a tedious and error-prone manual process. In this paper we present the first automatic face stabilization method that achieves professional-quality results on large sets of facial expressions. Since human faces can undergo a wide range of deformation, there is not a single point on the skin surface that moves rigidly with the underlying skull. Consequently, computing the rigid transformation from direct observation, a common approach in previous methods, is error prone and leads to inaccurate results. Instead, we propose to indirectly stabilize the expressions by explicitly aligning them to an estimate of the underlying skull using anatomically-motivated constraints.
How to read this
- Category
- Method: automatic rigid stabilization of facial expression scans
- Contributions
- The first automatic face stabilization method reaching professional-quality results on large sets of facial expressions
- Factors unwanted rigid head movement out of expression scans to recover true expression deformation, replacing a tedious manual production process
- An indirect stabilization approach that avoids the error-prone assumption that any skin point moves rigidly with the skull
- Context
- Builds on the authors' single-shot facial geometry capture (Beeler et al. 2010) and supports the digital-double scanning pipeline used in film and games.Builds on: High-Quality Single-Shot Capture of Facial Geometry
- Correctness
- Targets production-quality stabilization across wide facial deformation; its key premise is that no single skin point is truly rigid with the skull, so it stabilizes indirectly, and a reader should note results are validated on facial expression scan sets rather than against ground-truth skull motion.
- Clarity
- Clearly motivated by a concrete production pain point; a first pass conveys the problem and the indirect-stabilization insight, with a second pass for the optimization details.
- How to read it
- First pass for why direct rigid estimation fails and how indirect stabilization fixes it; second pass on the formulation only if integrating stabilization into a capture pipeline.
Builds on
Built upon by
Nothing yet.
Related work
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →