Graphics Reference
In-Depth Information
frame and the facial feature locations are detected. In the original system, it
is already done interactively via a GUI. In the future, we plan to detect these
feature locations automatically such that the whole fitting could be automatic.
Figure 4.1. Typical trackedframes and corresponding animated face models. (a): The input
image frames. (b): The tracking results visualized by yellow mesh overlayed on input images.
(c): The front views of the face model animated using tracking results. (d): The side views
of the face model animated using tracking results. In each row, the first image corresponds to
neutral face.
Search WWH ::




Custom Search