We present a novel method for acquisition, modeling, compression, and synthesis of
realistic facial deformations using polynomial displacement maps. Our method consists
of an analysis phase where the relationship between motion capture markers and detailed
facial geometry is inferred, and a synthesis phase where novel detailed animated facial
geometry is driven solely by a sparse set of motion capture markers. For analysis,
we record the actor wearing facial markers while performing a set of training expression clips.
We capture real-time high-resolution facial deformations, including dynamic wrinkle and pore detail, using interleaved structured light 3D scanning and photometric stereo. Next, we compute displacements between a neutral mesh driven by the motion capture markers and the high-resolution captured expressions. These geometric displacements are stored in a polynomial displacement map which is parameterized according to the local deformations of the motion capture dots. For synthesis, we drive the polynomial displacement map with new motion capture data. This allows the recreation of large-scale muscle deformation, medium and fine wrinkles, and dynamic skin pore detail. Applications include the compression of existing performance data and the synthesis of new performances.
Our technique is independent of the underlying geometry capture system and can be used to automatically generate high-frequency wrinkle and pore details on top of many existing facial animation systems.
Currently, creating realistic virtual faces often involves capturing textures,
geometry, and facial motion of real people. However, it is difficult to capture
and represent facial dynamics accurately at all scales. Face scanning systems can
acquire high-resolution facial textures and geometry, but typically only for static
poses. Motion capture techniques record continuous facial motion, but only at a
coarse level of detail. Straightforward techniques of driving high-resolution character
models by relatively coarse motion capture data often fails to produce realistic motion
at medium and fine scales (top image).
In this work, we introduce a novel automated method for modeling and synthesizing facial performances with realistic dynamic wrinkles and fine scale facial details. Our approach is to leverage a real-time 3D scanning system to record training data of the high-resolution geometry and appearance of an actor performing a small set of predetermined facial expressions. Additionally, a set of motion capture markers is placed on the face to track large scale deformations. Next, we relate these large scale deformations to the deformations at finer scales. We represent this relation compactly in the form of two deformation-driven polynomial displacement maps (PDMs), encoding variations in medium-scale and fine-scale displacements for a face undergoing motion (bottom image).
We synthesize new high-resolution geometry and surface detail from sparse motion capture markers using deformation-driven polynomial displacement maps; our results agree well with high-resolution ground truth geometry of dynamic facial performances.