The focus of our research is to develop numerical methods for physics simulations in computer graphics. A particular emphasis lies on simulating fluid flow with deep learning techniques, especially with convolutional neural networks. These methods have significant potential for efficient and robust simulations in the computer graphics and digital games context. Beyond this, we also target applications from the fields of mechanical engineering and medicine.
mantaflow: Many of our research projects are based on a common codebase, the mantaflow solver. This solver is an open-source framework targeted at fluid simulation research in Computer Graphics. It has a parallelized C++ solver core, a high-level python API for defining scenes and quickly adapting the solvers. It is tailored towards quickly prototyping and testing new algorithms. Recently, we’ve also added tools and plugins to interface with the tensorflow deep learning framework. The long term goal is to build a flexible platform for machine learning projects involving convolutional neural networks and fluid flow. Below, you can find an introduction to get started with manta & tensor-flow, and more detailed tutorials will follow soon.
Mantaflow-tensorflow coupling materials:
Mantaflow homepage: http://mantaflow.com
realFlow: A central research project is the ERC Starting Grant realFlow. The grant with a total volume of almost 1.5 million euro is aimed at novel simulation and reconstruction algorithms for fluid flows. The research project is titled “realFlow – Virtualization of Real Flows for Animation and Simulation” (StG-2015-637014). It’s goal is to improve the simulation of physical processes and, above all, make it possible to generate such simulations more quickly and realisitcally. A central component of this research are data-driven methods, especially machine learning techniques with neural networks.