arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11940cs.GRcs.AI
收藏

神经向量场控制的Wassersplines动画

Wassersplines for Neural Vector Field--Controlled Animation

Massachusetts Institute of Technology(麻省理工学院)

Paul Zhang, Dmitriy Smirnov, Justin Solomon

摘要:

许多计算机生成的动画都是通过使用装备操纵网格来创建的。虽然这种方法适用于动画连接对象,如动物,它有有限的灵活性,动画结构较少的自由形式的对象。我们介绍了Wassersplines,一种新的轨迹推理方法动画非结构化密度的基础上,在连续规范化的流量和最佳运输的最新进展。其关键思想是训练一个神经参数化的速度场,该速度场表示关键帧之间的运动。然后通过平流关键帧通过速度场来计算轨迹。我们解决了一个额外的Wasserstein重心插值问题,以保证严格遵守关键帧。我们的工具可以通过各种基于PDE的正则化器来设计轨迹,以创建不同的视觉效果。我们展示了我们的工具上的各种关键帧插值问题,以产生时间连贯的动画,而无需网格或索具。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑