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.
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.