Deep Fluids: A Generative Network for Parameterized Fluid Simulations

dc.contributor.authorKim, Byungsooen_US
dc.contributor.authorAzevedo, Vinicius C.en_US
dc.contributor.authorThuerey, Nilsen_US
dc.contributor.authorKim, Theodoreen_US
dc.contributor.authorGross, Markusen_US
dc.contributor.authorSolenthaler, Barbaraen_US
dc.contributor.editorAlliez, Pierre and Pellacini, Fabioen_US
dc.date.accessioned2019-05-05T17:39:25Z
dc.date.available2019-05-05T17:39:25Z
dc.date.issued2019
dc.description.abstractThis paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to the capability of deep learning architectures to learn representative features of the data, our generative model is able to accurately approximate the training data set, while providing plausible interpolated in-betweens. The proposed generative model is optimized for fluids by a novel loss function that guarantees divergence-free velocity fields at all times. In addition, we demonstrate that we can handle complex parameterizations in reduced spaces, and advance simulations in time by integrating in the latent space with a second network. Our method models a wide variety of fluid behaviors, thus enabling applications such as fast construction of simulations, interpolation of fluids with different parameters, time re-sampling, latent space simulations, and compression of fluid simulation data. Reconstructed velocity fields are generated up to 700x faster than re-simulating the data with the underlying CPU solver, while achieving compression rates of up to 1300x.en_US
dc.description.number2
dc.description.sectionheadersFluids
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume38
dc.identifier.doi10.1111/cgf.13619
dc.identifier.issn1467-8659
dc.identifier.pages59-70
dc.identifier.urihttps://doi.org/10.1111/cgf.13619
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13619
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectPhysical simulation
dc.subjectNeural networks
dc.titleDeep Fluids: A Generative Network for Parameterized Fluid Simulationsen_US
Files
Collections