Practical Dynamic Facial Appearance Modeling and Acquisition
TimeWednesday, 5 December 20184:41pm - 5:07pm
DescriptionWe present a method to acquire dynamic properties of facial skin appearance, including dynamic diffuse albedo encoding blood flow, dynamic specular BRDF properties as a function of surface deformation, and per frame high resolution normal maps for a sequence of facial performance. The method reconstructs these from a purely passive multi-camera setup, without the need for polarization or requiring to temporally modulate the illumination. It is hence very well suited for integration with existing passive facial performance capture systems.
We solve this highly challenging problem by modeling the relationship between skin deformation and surface reflectance, which allows to aggregate information from multiple frames over the course of an actor's performance. We further show that albedo changes due to blood flow are confined to a line in the CIE 1976 Lab color space, and we exploit this subspace for robustly estimating time varying albedo.
The presented method is the first system capable of capturing high-quality dynamic appearance maps at full resolution and video framerates, providing a major step forward in the area of facial appearance acquisition.