Method for generating an animated three-dimensional video head
The invention relates to a technique for generating an animated three-dimensional video head based on sensed locations of facial features and texture mapping of corresponding two dimensional video image frames onto a shaped head mesh generated using the sensed locations.
1. A method for generating a three-dimensional animated video head, comprising steps for:
capturing a sequence of two-dimensional video image frames of the face of an actor;
for each two-dimensional video image frame:
sensing the locations of the actor's facial features at predetermined node locations in the two-dimensional video image frame, wherein each node location is associated with a particular facial feature;
driving control points on a three-dimensional head mesh based on the sensed node locations in the two-dimensional video image frame to generate a shaped three-dimensional head mesh;
warping the two-dimensional video image frame used to generate the sensed node locations for projection onto the shaped head mesh; and
texture mapping the warped two-dimensional video image frame onto the shaped head mesh to generate a three-dimensional frame head associated with the respective two-dimensional video image frame; and
animating the three-dimensional video head by displaying a sequence of the three-dimensional frame heads associated with the sequence of two-dimensional video image frames.
2. Method for generating a three-dimensional animated video head as defined in claim 1 , wherein the step of sensing the locations of the actor's facial features at predetermined node locations in the two-dimensional video image frame is performed using a transformed facial image frame generated based on wavelet transformations.
3. Method for generating a three-dimensional animated video head as defined in claim 1 , wherein the step of sensing the locations of the actor's facial features at predetermined node locations in the two-dimensional video image frame is performed using a transformed facial image frame generated based on Gabor wavelet transformations.
4. Method for generating a three-dimensional animated video head as defined in claim 1 , wherein each two-dimensional image frame, in the sequence of two-dimensional video image frames, has only one view of the actor's face.