用神经物理+数值模拟实现低延迟实时流体交互仿真
Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time
- 混合神经与数值方法，保证实时性与物理准确性
- 11~29%延迟下实现高帧率2D/3D流体模拟
- 支持手绘草图控制流体运动，适合交互应用
我们提出一种用于实时交互式流体模拟的神经物理系统。传统物理方法虽准确但计算成本高、延迟大；近期机器学习方法降低算力需求，但仍难满足实时性要求且缺乏交互支持。为此，我们设计了一种新型混合方法，融合数值模拟、神经物理与生成控制。神经物理模块通过回退机制结合经典数值求解器，在追求低延迟与高物理保真度的同时确保稳定性。此外，我们开发基于扩散模型的控制器，采用逆向建模策略训练生成外力场，实现对流体的交互操控。系统在多种2D/3D场景、材质类型及障碍物交互下表现稳健，达到11~29%延迟的高帧率实时模拟，并支持用户友好的手绘草图引导控制。本工作为实时交互应用中的可控、物理可信流体模拟迈出关键一步。论文接受后将公开模型与数据。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。