LGCVGRJan 27, 2023

Learning Vortex Dynamics for Fluid Inference and Prediction

Stanford
arXiv:2301.11494v327 citationsh-index: 77
Originality Incremental advance
AI Analysis

This work addresses the challenge of learning fluid simulators from visual data for applications in computer graphics or physics-based modeling, but it appears incremental as it builds on particle-based and differentiable simulation techniques.

The authors tackled the problem of inferring and predicting fluid dynamics from a single video by proposing a differentiable vortex particle method, which improved reconstruction quality, visual plausibility, and physical integrity compared to existing methods.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes