Graphics Reference
In-Depth Information
When full correspondence between the face model and the scan data is established and the
new face instance is not redundant, it can be added as a new example to the statistical face
model, increasing the descriptiveness of the model. The process of using a statistical model to
enhance itself automatically, is referred to as
bootstrapping
the synthesis of the model. The
difficulty of bootstrapping is that (1) if the model (as is) fits a new example well, there is no use
of adding the new example to the model. This must be automatically verified. (2) If the model
doesn't fit the new example, the correspondences are incorrect and the example cannot be
added to the model. (3) It should be fully automatic. Nowadays, several statistical models are
available, ready to be used and reused. In this chapter, we present a bootstrapping algorithm
on the basis of an initial statistical model, which automatically fits to new scan data with noise
and holes, and which is capable of measuring the redundancy of new example faces.
The need for bootstrapping statistical models was posed by Vetter et al. (1997). They
introduced a bootstrapping algorithm for statistical models, and showed that the use of merely
an optic flow algorithmwas not enough to establish full correspondence between example faces
and a reference face. Instead, they attain an effective bootstrapping algorithm by iteratively
fitting the face model, applying the optic flow algorithm, and updating the face model. They
also used this bootstrapping algorithm to build a 3D morphable face model (Blanz and Vetter,
1999). Their bootstrapping algorithmworks well in case of input data with constant properties,
but fails when input data is incomplete and when the optic flow algorithm fails. To bootstrap
the 3D morphable face model with more general face data, (Basso et al., 2006) added a
smoothness term to regularize the positions of the vertices where the optic flow correspondence
is unreliable. In case a 3D morphable face model is not yet available, a reference face can be
used as an approximation instead, which is a major advantage.
Amberg et al. (2007) proposed a non rigid ICP algorithm to establish dense correspondences
between a reference face and face scans, but they need an initial rigid transformation for the
reference face on the basis of 14 manually selected landmarks. Afterwards, the reference face
and the fitted face instances can be used to construct a new morphable face model.
Basso and Verri (2007) fit the morphable face model to scan data using implicit represen-
tations. They also use multiple components and blend the implicit functions at the borders of
components, but they lose the full point-to-point correspondence in the process. So the fitted
examples cannot be added to the morphable model.
Huang et al. (2006) proposed a global-to-local deformation framework to deform a shape
with an arbitrary dimension (2D, 3D or higher) to a new shape of the same class. Their method
also operates in the space of implicit surfaces, but uses a non statistical deformation model.
They show their framework's applicability to 3D faces, for which they deform an incomplete
source face to a target face.
The use of multiple components has been used by to improve the face model fitting by Blanz
and Vetter (1999) and for face recognition purposes by Blanz and Vetter (2003), but, so far,
the resulting face instances were not accurate enough to be incorporated in the statistic model.
The explicit point-to-point correspondences of the fitted face instance and the statistical model
had to be established by techniques on the basis of optic flow or non rigid ICP.
In this chapter, a set of predefined face components was used to increase the descriptiveness
of a 3D morphable face model. With the use of multiple components, a tighter fit of the
face model was obtained and higher recognition rates were achieved. However, by fitting
each component individually, components started to intersect, move apart, or move across. So,
afterwards the full point-to-point correspondences between the morphable model and the fitted
