There are a vast number of factors involved in reproducing the subtleties of realistic facial animation. So many, in fact, that it is near impossible for an animator or a computer simulation to achieve genuinely realistic results. One reason for this is simply a lack of sufficient models for the important characteristics and subtle dynamics of facial expressions expected by human observers, who are all ultimate experts at watching faces! The Uncanny Valley has recently become the standard term for the unintentional creepy appearance of near-photoreal, computer generated, animated faces. This phenomenon, first predicted in the context of robotics, is being increasingly seen in human characters in video games. The work described here can be viewed as a direct attempt to build a bridge across the Uncanny Valley and start climbing up the other side for the most challenging applications of all for digital humans—those requiring real-time interactivity. Ultimately, we hope that our collection of techniques will help human characters in video games and other real-time applications to approach the believability and emotional impact offered by their film counterparts.