Learning Elastic Constitutive Material and Damping Models.

The fidelity of a deformation simulation is highly dependent upon the underlying constitutive material model. Commonly used linear and nonlinear constitutive material models contain many simplifications and only cover a tiny part of possible material behavior. In this work we propose a framework for learning customized models of deformable materials from sparse example surface trajectories. The key idea is to iteratively improve a correction to a nominal model of the elastic and damping properties of the object, which allows new forward simulations with the learned correction to more accurately predict the behavior of a given soft object. The challenge is that such data is sparse as it is typically available only on part of the surface. Sparse reduced space-time optimization identifies gentle control forces with which we extract necessary annotated data for model inference and to finally encapsulate the material correction into a compact parametric form. We demonstrate our method with a set of synthetic examples, as well as with data captured from real world homogeneous elastic objects.