Authors:
Bernhard Egger
;
Dinu Kaufmann
;
Sandro Schönborn
;
Volker Roth
and
Thomas Vetter
Affiliation:
University of Basel, Switzerland
Keyword(s):
Copula Component Analysis, Gaussian copula, Principal Component Analysis, Parametric Appearance Models, 3D Morphable Model, Face Modeling, Face Synthesis.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Fundamental Methods and Algorithms
;
Geometry and Modeling
;
Image-Based Modeling
;
Model Validation
;
Modeling and Algorithms
;
Pattern Recognition
;
Software Engineering
;
Texture Models, Analysis, and Synthesis
Abstract:
Principal component analysis is a ubiquitous method in parametric appearance modeling for describing dependency and variance in a data set. The method requires that the observed data be Gaussian-distributed. We show that this requirement is not fulfilled in the context of analysis and synthesis of facial appearance. The model mismatch leads to unnatural artifacts which are severe to human perception. In order to prevent these artifacts, we propose to use a semiparametric Gaussian copula model, where dependency and variance are modeled separately. The Gaussian copula enables us to use arbitrary Gaussian and non-Gaussian marginal distributions. The new flexibility provides scale invariance and robustness to outliers as well as a higher specificity in generated images. Moreover, the new model makes possible a combined analysis of facial appearance and shape data. In practice, the proposed model can easily enhance the performance obtained by principal component analysis in existing pipel
ines: The steps for analysis and synthesis can be implemented as convenient pre- and post-processing steps.
(More)