Dynamic Real-Time Deformations using Space and Time Adaptive Sampling
This paper presents the first robust method for animating dynamic visco-elastic
deformable objects that provides a guaranteed frame rate. The approach uses an automatic
space and time adaptive level of detail technique, in combination with a large-displacement
(Green) strain tensor formulation. The body is hierarchically partitioned into a number of
tetrahedral regions and mass samples. The local resolution is determined by a quality
condition that indicates where and when the resolution is too coarse. As the object moves and
deforms, the sampling is refined to concentrate the computational load into the regions that
deform the most. Our model consist of a continuous equation solved using a local explicit finite
element method. We demonstrate that our adaptive Green strain tensor formulation virtually
suppresses unwanted artifacts in the dynamic behavior, compared to adaptive mass-spring and other
adaptive approaches. In particular, damped elastic vibration modes are shown to be nearly
unchanged for several levels of refinement. Results are presented in the context of a virtual reality
system. The user interacts in real-time with the dynamic object (such as a liver) through the
control of a rigid tool, attached to a haptic device driven with forces derived from the method.
Images and movies
BibTex references
@InProceedings\{DDCB01, author = "Debunne, Gilles and Desbrun, Mathieu and Cani, Marie-Paule and Barr, Alan H.", title = "Dynamic Real-Time Deformations using Space and Time Adaptive Sampling", booktitle = "Computer Graphics Proceedings", series = "Annual Conference Series", month = "Aug", year = "2001", publisher = "ACM Press / ACM SIGGRAPH", note = "Proceeding", keywords = "animation, multiresolution, de", url = "http://artis.inrialpes.fr/Publications/2001/DDCB01" }