Physics-Informed Video Diffusion For Shallow Water Equations
This work addresses the need for efficient and physically accurate video generation in fluid dynamics, offering a domain-specific improvement over existing methods.
The paper tackled the problem of generating realistic fluid dynamics videos with high computational cost by proposing a physics-informed video diffusion framework that jointly generates visual outputs and physical states, resulting in outperforming data-driven baselines in realism and physical fidelity while being significantly faster than traditional pipelines.
Traditional fluid dynamics simulation pipelines combine numerical solvers with rendering, producing highly realistic results but at considerable computational cost. Diffusion-based generative video models offer a faster alternative, yet often ignore physical laws and thus fail to capture consistent dynamics. We propose a physics-informed video diffusion framework that jointly generates visual outputs and physical states. Unlike prior two-stage approaches that first simulate the physical variables and then render, we directly integrate physics constraints into the generative process, enabling simultaneous prediction of physical states and realistic videos without a separate rendering step. Built on the two-dimensional shallow water equations with terrain topography, our method produces temporally coherent water flow while maintaining physical plausibility. Experiments show that it outperforms purely data-driven video diffusion baselines in both realism and physical fidelity, while generating videos significantly faster than traditional simulation-plus-rendering pipelines.