MultiFloodSynth: Multi-Annotated Flood Synthetic Dataset Generation

2025-02-06

AI Summary

To address the scarcity of real-world annotated data and the bias introduced by hand-crafted synthetic data in flood detection, this paper proposes the first high-fidelity synthetic data generation framework tailored for flood detection. The framework integrates procedural urban modeling, physics-driven multi-level flood simulation, and state-of-the-art image-to-3D generation to controllably simulate realistic hydrodynamic processes within virtual cities, while simultaneously generating dense, multimodal annotations—including surface normal maps, semantic segmentation masks, and 3D bounding boxes. Unlike prior approaches, our method is the first to enable automatic, hierarchical, and multimodal annotation of synthetic flood scenes. Experiments demonstrate that models trained on our synthetic dataset achieve performance on par with those trained on real data, while significantly improving generalization and robustness across diverse scenes and sensor modalities.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Multimodal Learning

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

In this paper, we present synthetic data generation framework for flood hazard detection system. For high fidelity and quality, we characterize several real-world properties into virtual world and simulate the flood situation by controlling them. For the sake of efficiency, recent generative models in image-to-3D and urban city synthesis are leveraged to easily composite flood environments so that we avoid data bias due to the hand-crafted manner. Based on our framework, we build the flood synthetic dataset with 5 levels, dubbed MultiFloodSynth which contains rich annotation types like normal map, segmentation, 3D bounding box for a variety of downstream task. In experiments, our dataset demonstrate the enhanced performance of flood hazard detection with on-par realism compared with real dataset.

Problem

• Generates synthetic flood dataset
• Improves flood hazard detection
• Ensures high fidelity realism

Innovation

• Synthetic data generation framework
• Image-to-3D generative models
• Multi-level flood synthetic dataset