We propose a neural physics system for real-time, interactive fluid simulations. Traditional physics-based methods, while accurate, are computationally intensive and suffer from latency issues. Recent machine‑learning methods reduce computational costs while preserving fidelity; yet most still fail to satisfy the latency constraints for real‑time use and lack support for interactive applications. To bridge this gap, we introduce a novel hybrid method that integrates numerical simulation, neural physics, and generative control. Our neural physics jointly pursues low-latency simulation and high physical fidelity by employing a fallback safeguard to classical numerical solvers. Furthermore, we develop a diffusion-based controller that is trained using a revserve modeling strategy to generate external dynamic force fields for fluid manipulation. Our system demonstrates robust performance across diverse 2D/3D scenarios, material types, and obstacle interactions, achieving real-time simulations at high frame rates (11~29% latency) while enabling fluid control guided by user-friendly freehand sketches. We present a significant step towards practical, controllable, and physically plausible fluid simulations for real-time interactive applications.
Figure: Method Overview. To achieve real‑time simulations, we cut latency by learning neural physics at a coarse spatiotemporal resolution, while safeguarding fidelity by automatically falling back to an MPM solver when complex fluid phenomena arise. For interactive control, we train a diffusion-based generative model that infers external force fields directly from user sketches.
@article{xu2025hybrid,
title={Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time},
author={Xu, Jingxuan and Huang, Hong and Zou, Chuhang and Savva, Manolis and Wei, Yunchao and Chen, Wuyang},
journal={arXiv preprint arXiv:2505.18926},
year={2025}
}