arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.17152cs.CV
收藏

PhysFire-WM: 一种融合物理信息的世界模型用于模拟火灾扩散动力学

PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics

Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Department of Electronic Engineering, Tsinghua University(清华大学电子工程系)

Nan Zhou, Huandong Wang, Jiahao Li, Yang Li, Xiao-Ping Zhang, Yong Li, Xinlei Chen

AI总结:

PhysFire-WM通过融合物理信息和跨任务协作训练策略,提升火灾扩散预测的物理真实性和几何准确性。

摘要:

精细层面的火灾预测在应急响应中起着关键作用。红外图像和火灾掩膜提供了互补的热信息和边界信息,但当前方法主要局限于二值掩膜建模,具有固有的信号稀疏性,无法捕捉火灾的复杂动态。虽然世界模型在视频生成中展现出潜力,但其物理不一致性对火灾预测构成了重大挑战。本文介绍了PhysFire-WM,一种用于模拟火灾扩散动力学的融合物理信息的世界模型。我们的方法通过将物理模拟器中的结构先验编码纳入其中,以纠正物理不一致,同时结合跨任务协作训练策略(CC-Train),以缓解基于掩膜建模的信息有限问题。通过参数共享和梯度协调,CC-Train有效整合了热辐射动态和空间边界界定,提升了物理真实性和几何准确性。在细粒度多模态火灾数据集上的广泛实验验证了PhysFire-WM在火灾扩散预测中的优越准确性。验证强调了物理先验和跨任务协作的重要性,为将物理信息世界模型应用于灾难预测提供了新的见解。

英文摘要:

Fine-grained fire prediction plays a crucial role in emergency response. Infrared images and fire masks provide complementary thermal and boundary information, yet current methods are predominantly limited to binary mask modeling with inherent signal sparsity, failing to capture the complex dynamics of fire. While world models show promise in video generation, their physical inconsistencies pose significant challenges for fire forecasting. This paper introduces PhysFire-WM, a Physics-informed World Model for emulating Fire spread dynamics. Our approach internalizes combustion dynamics by encoding structured priors from a Physical Simulator to rectify physical discrepancies, coupled with a Cross-task Collaborative Training strategy (CC-Train) that alleviates the issue of limited information in mask-based modeling. Through parameter sharing and gradient coordination, CC-Train effectively integrates thermal radiation dynamics and spatial boundary delineation, enhancing both physical realism and geometric accuracy. Extensive experiments on a fine-grained multimodal fire dataset demonstrate the superior accuracy of PhysFire-WM in fire spread prediction. Validation underscores the importance of physical priors and cross-task collaboration, providing new insights for applying physics-informed world models to disaster prediction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑