4.5 Article

Deep Fluids: A Generative Network for Parameterized Fluid Simulations

期刊

COMPUTER GRAPHICS FORUM
卷 38, 期 2, 页码 59-70

出版社

WILEY
DOI: 10.1111/cgf.13619

关键词

-

资金

  1. Swiss National Science Foundation [200021_168997]
  2. ERC [637014]
  3. Swiss National Science Foundation (SNF) [200021_168997] Funding Source: Swiss National Science Foundation (SNF)
  4. European Research Council (ERC) [637014] Funding Source: European Research Council (ERC)

向作者/读者索取更多资源

This 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.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据