Authors:
Ozan Cetinaslan
1
;
John Lewis
2
and
Verónica Orvalho
1
Affiliations:
1
Universidade do Porto, Portugal
;
2
Victoria University, New Zealand
Keyword(s):
Blendshape, Facial Expression, Deformation, 3D Mesh, Facial Animation.
Related
Ontology
Subjects/Areas/Topics:
Animation Algorithms and Techniques
;
Animation and Simulation
;
Computer Vision, Visualization and Computer Graphics
;
Facial Animation
Abstract:
The blendshape approach is a predominant technique for creating high quality facial animation. Facial poses
are generated by altering the corresponding weight parameters manually for each key-frame by using traditional
slider interfaces. However, authoring a production quality facial animation with this process requires
time-consuming, labor intensive and iterative work the artists. Direct manipulation interfaces address this
problem with a “pin-and-drag” operation inspired by the inverse kinematics approaches. The mathematical
frameworks of the direct manipulation techniques are mostly based on pseudo-inverse of the blendshape matrices
which include all target shape’s vertex positions. However, the pseudo-inverse approaches often give
unexpected results during the facial pose editing process because of its unstable behavior. To this end, we
propose the transposition approach to enhance the direct manipulation by reducing unexpected movements
during weight editing. Our approach extra
cts the deformation directions from the blendshape matrix, and directly
maps the sparse constrained point movements to the extracted directions. Our experiments show that,
instead of psuedo-inverse based formulations, transposition based framework gives more smooth and reliable
facial poses during the weight editing process. The proposed approach improves the fidelity of the generated
facial expressions by keeping the hazardous movements in a minimum level. It is robust, efficient, easy to
implement and operate on any blendshape model.
(More)