ScalarFlow: A Large-Scale Volumetric Data Set of Real-world Scalar Transport Flows for Computer Animation and Machine Learning
This dataset provides a valuable resource for researchers in computer graphics, vision, and machine learning working with scalar transport flows, enabling the development and evaluation of new methods for simulating and analyzing complex real-world fluid dynamics.
This paper introduces ScalarFlow, a large-scale dataset of real-world smoke plume reconstructions, captured using a novel framework for physics-based reconstruction from a few video streams. The dataset includes complex, natural buoyancy-driven flows that transition to turbulent states, and a perceptual evaluation study shows that these flows require high simulation resolutions for recreation.
In this paper, we present ScalarFlow, a first large-scale data set of reconstructions of real-world smoke plumes. We additionally propose a framework for accurate physics-based reconstructions from a small number of video streams. Central components of our algorithm are a novel estimation of unseen inflow regions and an efficient regularization scheme. Our data set includes a large number of complex and natural buoyancy-driven flows. The flows transition to turbulent flows and contain observable scalar transport processes. As such, the ScalarFlow data set is tailored towards computer graphics, vision, and learning applications. The published data set will contain volumetric reconstructions of velocity and density, input image sequences, together with calibration data, code, and instructions how to recreate the commodity hardware capture setup. We further demonstrate one of the many potential application areas: a first perceptual evaluation study, which reveals that the complexity of the captured flows requires a huge simulation resolution for regular solvers in order to recreate at least parts of the natural complexity contained in the captured data.