Semantic Deformation Transfer

Ilya Baran     Daniel Vlasic     Eitan Grinspun     Jovan Popović

Semantic deformation transfer learns a correspondence between poses of two characters from example meshes and synthesizes new poses of the target character from poses of the source character. In this example, given five corresponding poses of two characters (left), our system creates new poses of the bottom character (right) from four poses of the top character.
Transferring motion.

Paper: PDF (SIGGRAPH 2009)
Video: AVI (DivX, 21MB, with sound)
Input data was obtained primarily from our previous year's project.


Transferring existing mesh deformation from one character to another is a simple way to accelerate the laborious process of mesh animation. In many cases, it is useful to preserve the semantic characteristics of the motion instead of its literal deformation. For example, when applying the walking motion of a human to a flamingo, the knees should bend in the opposite direction. Semantic deformation transfer accomplishes this task with a shape space that enables interpolation and projection with standard linear algebra. Given several example mesh pairs, semantic deformation transfer infers a correspondence between the shape spaces of the two characters. This enables automatic transfer of new poses and animations.

Back to my homepage