Wassersplines for Neural Vector Field--Controlled Animation
This provides a flexible animation tool for unstructured objects in computer graphics, though it is incremental as it builds on existing techniques like continuous normalizing flows and optimal transport.
The paper tackles the problem of animating unstructured free-form objects without meshing or rigging by introducing Wassersplines, a trajectory inference method that uses neural vector fields and optimal transport to interpolate keyframes, resulting in temporally-coherent animations as demonstrated on various problems.
Much of computer-generated animation is created by manipulating meshes with rigs. While this approach works well for animating articulated objects like animals, it has limited flexibility for animating less structured free-form objects. We introduce Wassersplines, a novel trajectory inference method for animating unstructured densities based on recent advances in continuous normalizing flows and optimal transport. The key idea is to train a neurally-parameterized velocity field that represents the motion between keyframes. Trajectories are then computed by advecting keyframes through the velocity field. We solve an additional Wasserstein barycenter interpolation problem to guarantee strict adherence to keyframes. Our tool can stylize trajectories through a variety of PDE-based regularizers to create different visual effects. We demonstrate our tool on various keyframe interpolation problems to produce temporally-coherent animations without meshing or rigging.