Cloth Simulation has been used widely in many industries such as fashion (design, online retail, etc.) and entertainment (games, movies, etc. ). However, realistic and fast cloth simulation is still a vastly open problem. For instance, realistic garment simulation is very difficult due to the low speed of high-fidelity simulation methods. This project aims to combine state-of-the-art theoretical research in cloth simulation, computer graphics and machine learning to target this problem. It will look into using cutting-edge machine learning techniques to accelerate various cloth simulation models. Further, it will look into new combined physical and machine learning models to automatically simulate fabrics with desired properties, such as to mimic real fabrics.
The project is currently accepting PhD applications every year.