混合神經-MPM實現即時互動流體模擬

Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time

May 25, 2025

作者: Jingxuan Xu, Hong Huang, Chuhang Zou, Manolis Savva, Yunchao Wei, Wuyang Chen

cs.AI

摘要

我們提出了一種用於即時互動流體模擬的神經物理系統。傳統基於物理的方法雖然精確，但計算量大且存在延遲問題。近期的機器學習方法在保持逼真度的同時降低了計算成本；然而，大多數方法仍無法滿足即時使用的延遲要求，並且缺乏對互動應用的支持。為彌補這一差距，我們引入了一種新穎的混合方法，該方法整合了數值模擬、神經物理和生成控制。我們的神經物理系統通過採用經典數值求解器的備用保障機制，同時追求低延遲模擬和高物理逼真度。此外，我們開發了一種基於擴散的控制器，該控制器使用逆向建模策略進行訓練，以生成用於流體操控的外部動態力場。我們的系統在多樣的2D/3D場景、材料類型及障礙物互動中展現了穩健的性能，實現了高幀率下的即時模擬（11~29%的延遲），並支持通過用戶友好的手繪草圖引導流體控制。我們在實現實用、可控且物理合理的即時互動流體模擬方面邁出了重要一步。我們承諾在論文被接受後將公開模型和數據。

English

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 reverse 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. We promise to release both models and data upon acceptance.