Show simple item record

dc.contributor.authorWiewel, Steffenen_US
dc.contributor.authorKim, Byungsooen_US
dc.contributor.authorAzevedo, Viniciusen_US
dc.contributor.authorSolenthaler, Barbaraen_US
dc.contributor.authorThuerey, Nilsen_US
dc.contributor.editorBender, Jan and Popa, Tiberiuen_US
dc.description.abstractWe propose an end-to-end trained neural network architecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on single-phase smoke simulations in 2D and 3D based on the incompressible Navier-Stokes (NS) equations, which are relevant for a wide range of practical problems. To achieve stable predictions for long-term flow sequences with linear execution times, a convolutional neural network (CNN) is trained for spatial compression in combination with a temporal prediction network that consists of stacked Long Short-Term Memory (LSTM) layers. Our core contribution is a novel latent space subdivision (LSS) to separate the respective input quantities into individual parts of the encoded latent space domain. As a result, this allows to distinctively alter the encoded quantities without interfering with the remaining latent space values and hence maximizes external control. By selectively overwriting parts of the predicted latent space points, our proposed method is capable to robustly predict long-term sequences of complex physics problems, like the flow of fluids. In addition, we highlight the benefits of a recurrent training on the latent space creation, which is performed by the spatial compression network. Furthermore, we thoroughly evaluate and discuss several different components of our method.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectPhysical simulation
dc.titleLatent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flowen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersFluids 1

Files in this item


This item appears in the following Collection(s)

  • 39-Issue 8
    ACM SIGGRAPH / Eurographics Symposium on Computer Animation 2020

Show simple item record