USC

ICT

GL

Facial Cartography: Interactive High-Resolution Scan Correspondence
ACM/Eurographics Symposium on Computer Animation (SCA) 2011 Paper
Cyrus A. Wilson     Oleg Alexander     Borom Tunwattanapong     Pieter Peers*     Abhijeet Ghosh    
Jay Busch     Arno Hartholt     Paul Debevec
USC Institute for Creative Technologies     The College of William & Mary*


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.

 

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.

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:

  1. image forces: favoring correspondences that provide the best alignment of fine-scale features in the detail maps;
  2. internal forces: avoiding physically implausible deformations by promoting an as-rigid-as-possible deformation;
  3. 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
  4. 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.

Please refer to the supplemental document for a more detailed description.

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.

 

Material:

SCA 2011 Paper:

SCA 2011 Video:

Related Projects:

© 2008 - 2013 USC Institute for Creative Technologies

Best Viewed in Firefox, Opera, Chrome and IE6 +