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.

翻译：对复杂场景中流体力学行为的建模在设计、图形学与机器人学等应用中至关重要。基于学习的方法提供了快速且可微的流体模拟器，然而现有大部分工作无法准确模拟流体与训练过程中未见过的全新曲面之间的相互作用。我们提出SURFSUP框架，该框架采用符号距离函数（SDF）隐式表示物体，而非使用网格或粒子的显式表示。这种几何的连续表示使得能够在延长的时间周期内更准确地模拟流体-物体相互作用，同时提升计算效率。此外，基于简单形状基元训练的SURFSUP能够实现显著的分布外泛化，甚至适用于复杂的真实场景与物体。最后，我们展示了可通过逆向该模型来设计简单物体以操控流体流动。