SurfsUp: Learning Fluid Simulation for Novel Surfaces
SurfsUp: Learning Fluid Simulation for Novel Surfaces
复制标题
DOI：
10.1109/iccv51070.2023.01308
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Arjun Mani;I. Chandratreya;Elliot Creager;Carl Vondrick;R. Zemel
中科院分区：
文献类型：
--
作者：
Arjun Mani;I. Chandratreya;Elliot Creager;Carl Vondrick;R. Zemel
对复杂场景中的流体力学进行建模对于设计、图形和机器人应用至关重要。基于学习的方法提供了快速和可区分的流体模拟器，然而大多数先前的工作无法准确地模拟流体如何与训练过程中看不到的真正新颖的表面相互作用。我们介绍SurfsUp，一个框架，表示对象隐式使用有符号的距离函数（SDF），而不是一个明确的表示网格或粒子。这种连续的几何表示能够更准确地模拟长时间内的流体-物体相互作用，同时使计算更有效。此外，在简单形状基元上训练的SurfsUp可以在很大程度上推广分布，甚至可以推广到复杂的现实世界场景和对象。最后，我们展示了我们可以反转我们的模型来设计简单的对象来操纵流体流动。
Modeling the mechanics of fluid in complex scenes is vital to applications in design, graphics, and robotics. Learning-based methods provide fast and differentiable fluid simulators, however most prior work is unable to accurately model how fluids interact with genuinely novel surfaces not seen during training. We introduce SurfsUp, a framework that represents objects implicitly using signed distance functions (SDFs), rather than an explicit representation of meshes or particles. This continuous representation of geometry enables more accurate simulation of fluid-object interactions over long time periods while simultaneously making computation more efficient. Moreover, SurfsUp trained on simple shape primitives generalizes considerably out-of-distribution, even to complex real-world scenes and objects. Finally, we show we can invert our model to design simple objects to manipulate fluid flow.