Abstract
Automatically generated anticipation is a largely
overlooked component of response in character motion for computer
animation. We present an approach for generating anticipation to
unexpected interactions with examples taken from human motion capture
data. Our system generates animation by quickly selecting an
anticipatory action using a Support Vector Machine (SVM) which is
trained offline to distinguish the characteristics of a given scenario
according to a metric that assesses predicted damage and energy
expenditure for the
character. We show our results for a character that can anticipate by
blocking or dodging a threat coming from a variety of locations and
targeting any part of the body, from head to toe.
Publications
Riverside
Graphics
Lab
(link)
Psychologically inspired anticipation and dynamic response for impacts
to the head and upper body.
Metoyer, R., Zordan, V.B., Hermens,
B., Wu, C.C., Soriano, M.
Transactions on Visual Computing and Graphics (TVCG) 2007 (in press)
[Paper]:
- pdf
[3.8MB]
[Videos]:
- movie
[49.4MB]
Riverside
Graphics
Lab
(link)
Anticpation
from
Example
Zordan, V.B., Macchietto, A., Medina,
J., Soriano, M., Wu, C.C., Metoyer, R., Rose, R.
ACM Virtual Reality Software and Technology (VRST) 2007 - to appear.
