Implicit Neural Representation for Physics-driven Actuated Soft Bodies
This work provides a general method for physics-driven animation of soft bodies, particularly useful for artists in domains like facial animation, though it appears incremental as it builds on existing differentiable simulation layers.
The paper tackles the problem of controlling active soft bodies by introducing an implicit neural representation for actuation signals, enabling continuous mapping and discretization-agnostic control, and demonstrates its application to facial animation, human poses, and volumetric bodies with reliable reproduction of expressions.
Active soft bodies can affect their shape through an internal actuation mechanism that induces a deformation. Similar to recent work, this paper utilizes a differentiable, quasi-static, and physics-based simulation layer to optimize for actuation signals parameterized by neural networks. Our key contribution is a general and implicit formulation to control active soft bodies by defining a function that enables a continuous mapping from a spatial point in the material space to the actuation value. This property allows us to capture the signal's dominant frequencies, making the method discretization agnostic and widely applicable. We extend our implicit model to mandible kinematics for the particular case of facial animation and show that we can reliably reproduce facial expressions captured with high-quality capture systems. We apply the method to volumetric soft bodies, human poses, and facial expressions, demonstrating artist-friendly properties, such as simple control over the latent space and resolution invariance at test time.