Performance Driven Facial Animation Course Notes Example: Motion Retargeting

When done correctly, a digitally recorded facial performance is an accurate measurement of the performer’s motions. As such it reflects all the idiosyncrasies of the performer. However, often the digital character that needs to be animated is not a digital replica of the performer. In this case, the decision to use performance capture might be motivated by cost issues, the desire to use a favorite actor regardless of the intended character, or the desire to portray an older, younger, or otherwise altered version of the actor. The many incarnations of Tom Hanks in Polar Express illustrate several of these scenarios. In this scenario, the recorded (source) performance has to be adapted to the target character. In this section of the course, we examine different techniques for retargeting or cross-mapping a recorded facial performance onto a digital face. We have grouped these techniques in several categories mostly as a function of whether they use a blendshape system for the source and/or the target face.