Our Fast Projective Skinning approach (FPS) introduces a two-layered model consisting of rigid bones and an elastic soft tissue layer that is efficiently constructed from a surface mesh of the character and its underlying skeleton. By developing a custom-tailored GPU implementation and a high-quality upsampling method, our approach is the first skinning method capable of detecting and handling arbitrary global collisions in real-time.

In the second part of our talk, we would like to briefly introduce our second model, which is restricted to human virtual characters but allows us to build an anatomically plausible three-layered representation of a person from a single surface scan in just a few seconds. It is composed of three surfaces for bones, muscles and skin enclosing the volumetric skeleton, muscles and fat tissues ant it can be used for physical simulation, statistical analysis and anatomical visualization in computer animation or in medical applications, which we demonstrate on several examples.