Wassersplines for Neural Vector Field--Controlled Animation

TL;DR

This paper introduces Wassersplines, a new method for animating unstructured densities by learning velocity fields with neural networks, enabling flexible, temporally-coherent animations without traditional rigging.

Contribution

The paper presents Wassersplines, a novel trajectory inference technique combining continuous normalizing flows and optimal transport for free-form object animation.

Findings

Produces smooth, temporally-coherent animations from keyframes

Does not require meshing or rigging for unstructured objects

Allows stylization of trajectories with PDE-based regularizers

Abstract

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.