用扩散模型从一张鱼眼图像生成逼真洪水，还能自由调控水位。
Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection
- 基于扩散模型，仅需一张鱼眼图生成真实洪水
- 可控制水位等物理变量，生成多样化洪水场景
- 适合城市防灾与异常检测研究者使用
针对城市灾害（如气候相关洪水）的物理仿真在防灾与异常检测中至关重要。然而，现实环境中洪水数据严重不足，加之鱼眼镜头影像固有的畸变，使高精度模拟面临挑战。为此，我们提出新系统PhysFlood，利用扩散模型仅凭一张鱼眼镜头图像即可合成逼真洪水。该系统不仅能实现单图生成，还可通过操控水位等物理变量自由生成多样洪水场景。评估实验中，定性人类研究表明，PhysFlood生成的图像兼具可接受的真实感与鲁棒性。
原文摘要 · Abstract (English)
Physical simulations that predict the behavior of urban disasters, such as climate-related flooding, play a crucial role in disaster prevention and the development of anomaly detection models. However, the severe shortage of flood data in real-world environments, combined with the inherent distortions of fisheye lens images, which are used for urban surveillance, has made high-precision simulations challenging. To address this, we propose a new physical simulation system PhysFlood that leverages Diffusion Models to synthesize realistic floods from just a single image captured by a fisheye lens. Our system not only enables simulation from a single image, but also features the ability to freely control and generate diverse flood scenarios by manipulating physically meaningful variables, such as water levels. In our evaluation experiments, we conducted a qualitative human study and demonstrated that the simulation images generated by PhysFlood exhibit both acceptable realism and robustness.
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。