mlsanityData to 14 Oct 2026

Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection

arXiv 2607.15527 ↗First posted 17 Jul 2026cs.CVcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 33 of its 41 references that are in the map. First posted on arXiv 17 Jul 2026.

Builds on

33 of 41 references.

References · 33

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  8. 2014Conditional Generative Adversarial Netscited by 2,162
  9. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  10. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  12. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
21 more
  1. 2025SAM 3: Segment Anything with Conceptscited by 906
  2. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  3. 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181
  4. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
  5. 2025YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detectioncited by 79
  6. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 62
  7. 2020Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baselinecited by 42
  8. 2022ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Fieldcited by 37
  9. 2019Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehiclescited by 25
  10. 2021Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flowcited by 23
  11. 2023FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detectioncited by 22
  12. 2024RAD: Region-Aware Diffusion Models for Image Inpaintingcited by 20
  13. 2025Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasetscited by 20
  14. 2021ClimateGAN: Raising Climate Change Awareness by Generating Images of Floodscited by 14
  15. 2025WeatherEdit: Controllable Weather Editing with 4D Gaussian Fieldcited by 12
  16. 2026GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deploymentcited by 8
  17. 2024FLAME Diffuser: Wildfire Image Synthesis using Mask Guided Diffusioncited by 5
  18. 2020Using Simulated Data to Generate Images of Climate Changecited by 4
  19. 2025Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspectivecited by 3
  20. 2021Deep Sensing of Urban Waterloggingcited by 2
  21. 2025ClimateGS: Real-Time Climate Simulation with 3D Gaussian Style Transfercited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Flood-LDM: Generalizable Latent Diffusion Models for rapid and accurate zero-shot High-Resolution Flood Mapping
  2. 2026Physics-Informed Video Diffusion For Shallow Water Equations
  3. 2026Deep Learning for Remote Sensing to Improve Flood Inundation Mapping
  4. 2026Forged Calamity: Benchmark for Cross-Domain Synthetic Disaster Detection in the Age of Diffusion
  5. 2025Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection
  6. 2025Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse Observations
  7. 2026Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation
  8. 2026FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation