Generating Liquid Simulations with Deformation-aware Neural Networks
This work addresses the challenge of efficiently simulating liquids with topology changes for applications in computer graphics and interactive media, representing an incremental improvement through a hybrid neural network method.
The paper tackles the problem of generating liquid simulations with complex, non-linear behavior under varying conditions by proposing a deformation-aware neural network approach that learns to weight and synthesize dense volumetric deformation fields, enabling rapid generation of implicit surfaces and real-time interactions in a mobile application.
We propose a novel approach for deformation-aware neural networks that learn the weighting and synthesis of dense volumetric deformation fields. Our method specifically targets the space-time representation of physical surfaces from liquid simulations. Liquids exhibit highly complex, non-linear behavior under changing simulation conditions such as different initial conditions. Our algorithm captures these complex phenomena in two stages: a first neural network computes a weighting function for a set of pre-computed deformations, while a second network directly generates a deformation field for refining the surface. Key for successful training runs in this setting is a suitable loss function that encodes the effect of the deformations, and a robust calculation of the corresponding gradients. To demonstrate the effectiveness of our approach, we showcase our method with several complex examples of flowing liquids with topology changes. Our representation makes it possible to rapidly generate the desired implicit surfaces. We have implemented a mobile application to demonstrate that real-time interactions with complex liquid effects are possible with our approach.