Active Learning for Interactive Audio-Animatronic Performance Design
share
We present a practical neural computational approach for interactive design of Audio-Animatronic® facial performances. An offline quasi-static reference simulation, driven by a coupled mechanical assembly, accurately predicts hyperelastic skin deformations. To achieve interactive digital pose design, we train a shallow, fully connected neural network (KSNN) on input motor activations to solve the simulated mesh vertex positions. Our fully automatic synthetic training algorithm enables a first-of-its-kind learning active learning framework (GEN-LAL) for generative modeling of facial pose simulations. With adaptive selection, we significantly reduce training time to within half that of the unmodified training approach for each new Audio-Animatronic® figure.
READ FULL TEXT