Tech & Research
Accurate markerless jaw tracking for facial performance capture
Disney Research presents a method for tracking the invisible jaw bone of an actor based solely on footage of the head, without the need for any markers. According to the paper, it works by "learning a non-linear mapping from the skin deformation to the underlying jaw motion on a dataset where ground-truth jaw poses have been acquired, and then to retarget the mapping to new subjects." Read the publication on the Disney Research website and watch a demo on YouTube.