arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.09668cs.CV
收藏

DiffWind: 基于物理的可微风驱物体动力学建模

DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics

State Key Laboratory of CAD & CG(CAD与计算机图形学国家重点实验室);State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室);Ant Group(蚂蚁集团);Shenzhen University(深圳大学)

Yuanhang Lei, Boming Zhao, Zesong Yang, Xingxuan Li, Tao Cheng, Haocheng Peng, Ru Zhang, Yang Yang, Siyuan Huang, Yujun Shen, Ruizhen Hu, Hujun Bao, Zhaopeng Cui

AI总结:

本文提出DiffWind,一种基于物理的可微框架,统一了风-物体相互作用建模、基于视频的重建和正向模拟。通过将风表示为基于网格的物理场,物体表示为从3D高斯点散布派生的粒子系统,并利用材料点方法(MPM)建模其相互作用,从而实现了对风驱物体动力学的重建。此外,本文还引入了WD-Objects数据集,通过大量实验证明了该方法在重建精度和模拟保真度方面显著优于现有动态场景建模方法。

摘要:

从视频观测建模风驱物体动力学极具挑战性,因为风的不可见性和时空变异性以及物体的复杂变形。我们提出了DiffWind,一种基于物理的可微框架,统一了风-物体相互作用建模、基于视频的重建和正向模拟。具体来说,我们将风表示为基于网格的物理场,物体表示为从3D高斯点散布派生的粒子系统,其相互作用通过材料点方法(MPM)建模。为了恢复风驱物体动力学,我们引入了一个重建框架,通过可微渲染和模拟联合优化时空风力场和物体运动。为了确保物理有效性,我们将其纳入格子玻尔兹曼方法(LBM)作为物理约束,强制符合流体动力学定律。除了重建之外,我们的方法自然支持在新型风条件下进行正向模拟,并能够实现新的应用,如风引导重定向。我们进一步引入了WD-Objects,一个合成和现实世界风驱场景的数据集。大量实验表明,我们的方法在重建精度和模拟保真度方面显著优于现有动态场景建模方法,为基于视频的风-物体相互作用建模开辟了新的途径。

英文摘要:

Modeling wind-driven object dynamics from video observations is highly challenging due to the invisibility and spatio-temporal variability of wind, as well as the complex deformations of objects. We present DiffWind, a physics-informed differentiable framework that unifies wind-object interaction modeling, video-based reconstruction, and forward simulation. Specifically, we represent wind as a grid-based physical field and objects as particle systems derived from 3D Gaussian Splatting, with their interaction modeled by the Material Point Method (MPM). To recover wind-driven object dynamics, we introduce a reconstruction framework that jointly optimizes the spatio-temporal wind force field and object motion through differentiable rendering and simulation. To ensure physical validity, we incorporate the Lattice Boltzmann Method (LBM) as a physics-informed constraint, enforcing compliance with fluid dynamics laws. Beyond reconstruction, our method naturally supports forward simulation under novel wind conditions and enables new applications such as wind retargeting. We further introduce WD-Objects, a dataset of synthetic and real-world wind-driven scenes. Extensive experiments demonstrate that our method significantly outperforms prior dynamic scene modeling approaches in both reconstruction accuracy and simulation fidelity, opening a new avenue for video-based wind-object interaction modeling.

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。

↑