FluidsNet: End-to-end learning for Lagrangian fluid simulation
FluidsNet: End-to-end learning for Lagrangian fluid simulation
复制标题
FluidsNet：拉格朗日流体模拟的端到端学习
DOI：
10.1016/j.eswa.2020.113410
复制
发表时间：
2020
影响因子：
8.5
通讯作者：
Wu Di
中科院分区：
文献类型：
--
作者：
Yalan Zhang;Xiaojuan Ban;Feilong Du;Wu Di
在过去的几十年中，流体模拟已成为计算机动画中的一个重要工具。然而，传统的基于物理的流体模拟系统耗时，并且需要大量的计算资源来生成大规模的流体流动。智能系统为我们提供了一种数据驱动的新方法来加速模拟。先前的智能系统通过使用基于上下文的积分方法手动构建特征向量，导致了较高的计算和内存需求。与现有技术不同，我们不使用任何手动构建的特征，而是直接对拉格朗日流体模拟数据进行操作并使用机器学习到的特征。本文提出了一种新颖的端到端深度学习神经网络，它能够基于拉格朗日流体模拟数据自动生成流体动画模型。这种方法使用神经网络合成具有不规则拉格朗日数据结构的速度场。每个流体粒子都被独立且相同地对待。我们使用对称函数来捕捉空间结构以及粒子之间的相互作用，并设计不同的网络结构来学习流体的各种层次特征。我们使用多个数据集以及在不同大小的各种场景中的应用对该方法进行了测试。我们的实验表明，该模型能够推断出具有诸如飞溅等逼真细节的速度场。此外，与现有的模拟系统相比，这种方法在速度上有显著提升，尤其是在大型场景模拟中。
Over the past few decades, fluid simulation has emerged as an important tool in computer animation. However, traditional physical-based fluid simulation systems are time consuming and requires large computational resources to generate large-scale fluid flows. Intelligent systems provide us a new method of data-driven to accelerate simulations. Previous intelligent system manually crafted feature vectors by using a context-based integral method and resulted in high computational and memory requirements. Unlike the existing techniques, we do not use any manually crafted feature, instead directly operate on Lagrangian fluid simulation data and use machine learned features. This paper presents a novel end-to-end deep learning neural network that can automatically generate a model for fluid animation based-on Lagrangian fluid simulation data. This approach synthesizes velocity fields with irregular Lagrangian data structure using neural network. Every fluid particle is treated independently and identically. We use symmetric functions to capture space structure and interactions among particles and design different network structures to learn various hierarchical features of fluid. We test this method using several data sets and applications in various scenes with different sizes. Our experiments show that the model is able to infer velocity field with realistic details such as splashes. In addition, compared with exiting simulation system, this method shows significant speed-ups, especially on large scene simulations.