Abstract
Physically plausible fluid simulations play an important role in modern computer graphics and engineering. However, in order to achieve real-time performance, computational speed needs to be traded-off with physical accuracy. Surrogate fluid models based on neural networks (NN) have the potential to achieve both fast fluid simulations and high physical accuracy. However, these approaches rely on massive amounts of training data, require complex pipelines for training and inference, or do not generalize to new fluid domains. In this work, we present significant extensions to a recently proposed deep learning framework, which addresses the aforementioned challenges in two dimensions (2D). We go from 2D to three dimensions (3D) and propose an efficient architecture to cope with the high demands of 3D grids in terms of memory and computational complexity. Furthermore, we condition the neural fluid model on additional information about the fluid's viscosity and density, which allows for simulating laminar as well as turbulent flows based on the same surrogate model. Our method allows us to train fluid models without requiring fluid simulation data beforehand. Inference is fast and simple, as the fluid model directly maps a fluid state and boundary conditions at a moment t to a subsequent fluid state at t + dt. We obtain real-time fluid simulations on a 128 × 64 × 64 grid that include various fluid phenomena such as the Magnus effect or Kármán vortex streets and generalize to domain geometries not considered during training. Our method indicates strong improvements in terms of accuracy, speed, and generalization capabilities over current 3D NN-based fluid models.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have