Abstract

We present a semi-automatic technique for computing surface correspondences between 3D facial scans in different expressions, such that scan data can be mapped into a common domain for facial animation. The technique can accurately correspond high-resolution scans of widely differing expressions -- without requiring intermediate pose sequences -- such that they can be used, together with reflectance maps, to create high-quality blendshape-based facial animation. We optimize correspondences through a combination of Image, Shape, and Internal forces, as well as Directable forces to allow a user to interactively guide and refine the solution. Key to our method is a novel representation, called an Active Visage, that balances the advantages of both deformable templates and correspondence computation in a 2D canonical domain. We show that our semi-automatic technique achieves more robust results than automated correspondence alone, and is more precise than is practical with unaided manual input.

Figure 1: Morph sequence between scans of neutral pose and corresponded extreme pose. Low-resolution meshes and high-resolution texture and normal maps are blended to give a high-quality result rendered in real-time.

Method

A key component in our system is an active visage: a proxy for representing corresponded blendshapes. While conceptually similar to a deformable template, a key difference is that a deformable template deforms a 3D mesh, while an active visage is constrained to the manifold of the non-neutral expression geometry, and hence only deforms the correspondences (this implies no 3D error).

We have developed a modular optimization framework in which four different forces act on these active visages to compute accurate correspondences. These four forces are:

• image forces: favoring correspondences that provide the best alignment of fine-scale features in the detail maps;
• internal forces: avoiding physically implausible deformations by promoting an as-rigid-as-possible deformation;
• shape forces: guiding the optimization estimate (along the expression geometry manifold) to result in a deformed template which more closely resembles a target 3D shape; and
• user directable forces that in conjuction with a GPU implementation of the other forces, enable the user to participate in the optimization process, and guide the optimization.

Results

While fully-automatic techniques exist, they often fail on difficult cases (e.g., extreme expressions), requiring one to handle such cases manually. However with a manual approach it is impractical to precisely align fine-scale details (such as skin pores), as seen in Figure 2. Alignment of such features is important if high-resolution detail maps are to be blended seamlessly, without introducing ghosting artifacts.

In our approach the artist and computer interact: the artist guides the optimization, as needed, through difficult or ambiguous situations; and the computation refines the optimization on the local scale (Figure 2). Figure 1 shows a blend between two expressions which have been corresponded using our technique. The correspondences obtained with this technique enable us to convincingly blend high-resolution maps. See the video for additional examples.

Downloads

SCA 2011 Paper
ACM
SCA2011_Paper.pdf, (16MB)
SCA2011_Supplement.pdf, (25.2MB)

SCA 2011 Video
SCA2011_FCvideo.mov, (136MB)

Related Projects

Light Stage 5
Rapid Acquisition of Specular and Diffuse Normal Maps from Polarized Spherical Gradient Illumination, EGSR 2007
Facial Performance Synthesis using Deformation-Driven Polynomial Displacement Maps, SIGGRAPH Asia 2008
High Resolution Face Scanning for "Digital Emily", ICT & Image Metrics Collaboration