In this work, we introduce an efficient and intuitive framework to produce synthetic multi-modal datasets of fluid simulations. The proposed pipeline can reproduce the dynamics of fluid flows and allows for exploring and learning various properties of their complex behavior from distinct perspectives and modalities. We aim to exploit these properties to fulfill the community's need for standardized training data, fostering more reproducible and robust research. We employ our framework to generate a set of thoughtfully designed training datasets, which attempt to span specific fluid simulation scenarios meaningfully. We demonstrate the properties of our contributions by evaluating recently published algorithms for the neural fluid simulation and fluid inverse rendering tasks using our benchmark datasets.
Efficient Generation of Multimodal Fluid Simulation Data
Maggioli F;
2024-01-01
Abstract
In this work, we introduce an efficient and intuitive framework to produce synthetic multi-modal datasets of fluid simulations. The proposed pipeline can reproduce the dynamics of fluid flows and allows for exploring and learning various properties of their complex behavior from distinct perspectives and modalities. We aim to exploit these properties to fulfill the community's need for standardized training data, fostering more reproducible and robust research. We employ our framework to generate a set of thoughtfully designed training datasets, which attempt to span specific fluid simulation scenarios meaningfully. We demonstrate the properties of our contributions by evaluating recently published algorithms for the neural fluid simulation and fluid inverse rendering tasks using our benchmark datasets.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
