Pre-computed Liquid Spaces with Generative Neural Networks and Optical Flow
share
Liquids exhibit highly complex, non-linear behavior under changing simulation conditions such as user interactions. We propose a method to map this complex behavior over a parameter range onto a reduced representation based on space-time deformations. In order to represent the complexity of the full space of inputs, we use deformations from optical flow solves with an improved alignment procedure, and we leverage the power of generative neural networks to synthesize additional deformations for refinement. We introduce a novel deformation-aware loss function, which enables optimization in the highly non-linear space of multiple deformations. To demonstrate the effectiveness of our approach, we showcase the method with several complex examples in two and four dimensions. Our representation makes it possible to rapidly generate implicit surfaces of liquids, which allows us to very efficiently display the scene from any angle, and to add secondary effects such as splash and foam particles. We have implemented a mobile application with our full pipeline to demonstrate that real-time interactions with complex liquid effects are possible with our approach. Our app yields effective speed-ups of several orders of magnitude compared to a regular simulation.
READ FULL TEXT
