Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors
This work addresses the challenge of generating realistic fluid simulations for computer graphics applications, offering an incremental improvement over existing methods by enhancing efficiency and detail.
The paper tackles the problem of synthesizing high-resolution smoke flow simulations by introducing a data-driven algorithm that uses CNN-based feature descriptors and a deformation limiting patch advection method, resulting in efficient, resolution-independent volumes with high effective resolutions and non-dissipative small-scale details.
We present a novel data-driven algorithm to synthesize high-resolution flow simulations with reusable repositories of space-time flow data. In our work, we employ a descriptor learning approach to encode the similarity between fluid regions with differences in resolution and numerical viscosity. We use convolutional neural networks to generate the descriptors from fluid data such as smoke density and flow velocity. At the same time, we present a deformation limiting patch advection method which allows us to robustly track deformable fluid regions. With the help of this patch advection, we generate stable space-time data sets from detailed fluids for our repositories. We can then use our learned descriptors to quickly localize a suitable data set when running a new simulation. This makes our approach very efficient, and resolution independent. We will demonstrate with several examples that our method yields volumes with very high effective resolutions, and non-dissipative small scale details that naturally integrate into the motions of the underlying flow.