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.
翻译:我们提出一种新的不同的旋涡粒子(DVP) 方法来从单一视频中推断和预测流体动态。 处于其核心的是一个粒子潜伏空间, 用来封装隐藏的、 Lagrangian vortical 进化, 支撑着可见的, Eulelian 流现象。 我们不同的旋涡粒子与一个可学习的、 旋流到速度动态映射相结合, 以有效捕捉物理控制、 低维度空间的复杂流动特征。 这个表达方式有助于学习一个适合输入视频的流体模拟器, 能够提供稳健的、 长期的未来预测。 我们的方法具有双重价值 : 首先, 我们所学的模拟器可以推断隐藏的物理数量( 例如, 速度场) 纯粹来自视觉观察; 第二, 它也支持未来的预测, 构建输入视频的后继物及其未来动态演进。 我们将我们的方法与合成视频和现实世界视频上的一系列现有方法进行比较, 显示重建质量的改进、 视觉可辨识性和物理完整性。