Learning Vortex Dynamics for Fluid Inference and Prediction
Learning Vortex Dynamics for Fluid Inference and Prediction
复制标题
DOI：
10.48550/arxiv.2301.11494
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Yitong Deng;Hong-Xing Yu;Jiajun Wu;Bo Zhu
中科院分区：
文献类型：
--
作者：
Yitong Deng;Hong-Xing Yu;Jiajun Wu;Bo Zhu
我们提出了一种新颖的可微涡旋粒子（DVP）方法，用于从单个视频推断和预测流体动力学。其核心是一个基于粒子的潜在空间，用于封装支撑可观测的欧拉流现象的隐藏的拉格朗日涡旋演化。我们的可微涡旋粒子与一个可学习的涡旋到速度的动力学映射相结合，以便在一个受物理约束的低维空间中有效地捕捉复杂的流动特征。这种表示有助于学习针对输入视频定制的流体模拟器，该模拟器能够提供稳健的长期未来预测。我们方法的价值有两方面：首先，我们所学习的模拟器能够纯粹从视觉观察推断出隐藏的物理量（例如速度场）；其次，它还支持未来预测，构建输入视频的后续内容及其未来的动力学演化。我们在合成视频和真实世界视频上与一系列现有方法进行了比较，展示了改进的重建质量、视觉合理性和物理完整性。
We propose a novel differentiable vortex particle (DVP) method to infer and predict fluid dynamics from a single video. Lying at its core is a particle-based latent space to encapsulate the hidden, Lagrangian vortical evolution underpinning the observable, Eulerian flow phenomena. Our differentiable vortex particles are coupled with a learnable, vortex-to-velocity dynamics mapping to effectively capture the complex flow features in a physically-constrained, low-dimensional space. This representation facilitates the learning of a fluid simulator tailored to the input video that can deliver robust, long-term future predictions. The value of our method is twofold: first, our learned simulator enables the inference of hidden physics quantities (e.g., velocity field) purely from visual observation; secondly, it also supports future prediction, constructing the input video's sequel along with its future dynamics evolution. We compare our method with a range of existing methods on both synthetic and real-world videos, demonstrating improved reconstruction quality, visual plausibility, and physical integrity.