DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913139323305984 |
|---|---|
| author | Lei, Yuanhang Zhao, Boming Yang, Zesong Li, Xingxuan Cheng, Tao Peng, Haocheng Zhang, Ru Yang, Yang Huang, Siyuan Shen, Yujun Hu, Ruizhen Bao, Hujun Cui, Zhaopeng |
| author_facet | Lei, Yuanhang Zhao, Boming Yang, Zesong Li, Xingxuan Cheng, Tao Peng, Haocheng Zhang, Ru Yang, Yang Huang, Siyuan Shen, Yujun Hu, Ruizhen Bao, Hujun Cui, Zhaopeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09668 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics Lei, Yuanhang Zhao, Boming Yang, Zesong Li, Xingxuan Cheng, Tao Peng, Haocheng Zhang, Ru Yang, Yang Huang, Siyuan Shen, Yujun Hu, Ruizhen Bao, Hujun Cui, Zhaopeng Computer Vision and Pattern Recognition 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. |
| title | DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.09668 |