Fakultät Informatik

Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors

 Mengyu Chu and  Nils Thuerey
Technical University of Munich, Germany
Conditionally accepted for ACM Transactions on Graphics (SIGGRAPH 2017)


Abstract

We present a novel data-driven algorithm to synthesize high resolution flow simulations with reusable repositories of space-time flow data. In our work, we employ a descriptor learning approach to encode the similarity between fluid regions with differences in resolution and numerical viscosity. We use convolutional neural networks to generate the descriptors from fluid data such as smoke density and flow velocity. At the same time, we present a deformation limiting patch advection method which allows us to robustly track deformable fluid regions. With the help of this patch advection, we generate stable space-time data sets from detailed fluids for our repositories. We can then use our learned descriptors to quickly localize a suitable data set when running a new simulation. This makes our approach very efficient, and resolution independent. We will demonstrate with several examples that our method yields volumes with very high effective resolutions, and non-dissipative small scale details that naturally integrate into the motions of the underlying flow.

Acknowledgements

This work was supported by the the ERC Starting Grant 637014.


  

 

News

Matthias Niessner, our new Professor from Stanford University, offers a number of interesting topics for  master theses.

 

PhD positions on   Computational Fabrication and 3D Printing and  Photorealistic Rendering for Deep Learning and Online Reconstruction are available at the Computer Graphics & Visualization group.