Xie Xueguang, Gao Yang, Hou Fei, Cheng Tianwei, Hao Aimin, Qin Hong
IEEE Trans Vis Comput Graph. 2025 Mar;31(3):1785-1801. doi: 10.1109/TVCG.2024.3370551. Epub 2025 Jan 30.
In this study, we devise a framework for volumetrically reconstructing fluid from observable, measurable free surface motion. Our innovative method amalgamates the benefits of deep learning and conventional simulation to preserve the guiding motion and temporal coherence of the reproduced fluid. We infer surface velocities by encoding and decoding spatiotemporal features of surface sequences, and a 3D CNN is used to generate the volumetric velocity field, which is then combined with 3D labels of obstacles and boundaries. Concurrently, we employ a network to estimate the fluid's physical properties. To progressively evolve the flow field over time, we input the reconstructed velocity field and estimated parameters into the physical simulator as the initial state. Our approach yields promising results for both synthetic fluid generated by different fluid solvers and captured real fluid. The developed framework naturally lends itself to a variety of graphics applications, such as 1) effective reproductions of fluid behaviors visually congruent with the observed surface motion, and 2) physics-guided re-editing of fluid scenes. Extensive experiments affirm that our novel method surpasses state-of-the-art approaches for 3D fluid inverse modeling and animation in graphics.
在本研究中，我们设计了一个框架，用于从可观察、可测量的自由表面运动中对流体进行体积重建。我们的创新方法融合了深度学习和传统模拟的优点，以保留再现流体的引导运动和时间连贯性。我们通过对表面序列的时空特征进行编码和解码来推断表面速度，并使用三维卷积神经网络（3D CNN）生成体积速度场，然后将其与障碍物和边界的三维标签相结合。同时，我们使用一个网络来估计流体的物理属性。为了随着时间逐步演化流场，我们将重建的速度场和估计的参数作为初始状态输入到物理模拟器中。我们的方法对于由不同流体求解器生成的合成流体和捕获的真实流体都产生了有前景的结果。所开发的框架自然适用于各种图形应用，例如1）有效地再现与观察到的表面运动视觉上一致的流体行为，以及2）对流体场景进行物理引导的重新编辑。大量实验证实，我们的新方法在图形学中3D流体逆向建模和动画方面超越了现有方法。
