发表机构
NEC Laboratories America（美国 NEC 实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DamageScope是一种结合VLMs与LLMs的检索增强框架，通过多向量嵌入聚类和双存储架构，实现了卫星图像灾害损失评估的高效自动化，可扩展性与运营效率优异。
AI 中文摘要
在自然灾害发生后，及时准确地评估财产损失至关重要。传统现场检查方式费力、成本高昂，且往往存在安全风险。卫星图像与视觉-语言模型（VLMs）的进展使大规模远程灾害损失评估成为可能，但将VLMs集成到大规模地球观测流程中存在计算效率、数据组织和信息检索方面的挑战。为应对这些挑战，本文提出DamageScope，这是一种检索增强框架，结合卫星图像、视觉-语言模型（VLMs）和大语言模型（LLMs）以实现财产损失分析自动化。DamageScope构建于检索增强生成（RAG）框架之上，从卫星图像中提取结构化视觉表示，以支持针对灾害损失评估的交互式自然语言查询。为解决可扩展性问题，本文引入一种新型多向量嵌入聚类算法，其性能优于传统单向量嵌入方法，同时将索引时间最多降低14倍。此外，双存储数据架构可最小化LLM API调用，将运营成本和响应延迟最多降低约3倍。通过有效平衡可扩展性与运营效率，DamageScope为实际灾害损失评估任务提供了一种稳健且实用的解决方案。
英文摘要
Timely and accurate assessment of property damage is critical following natural disasters. Traditional on-site inspections are labor-intensive, costly, and often pose safety risks. Advances in satellite imagery and vision-language models (VLMs) enable scalable remote damage assessment; however, integrating VLMs into large-scale Earth observation pipelines presents challenges in computational efficiency, data organization, and information retrieval. To address these challenges, we present DamageScope, a retrieval-augmented framework that combines satellite imagery with Vision-Language Models (VLMs) and Large Language Models (LLMs) to automate property damage analysis. Built on a Retrieval-Augmented Generation (RAG) framework, DamageScope extracts structured visual representations from satellite imagery to support interactive natural language queries for damage assessment. To address scalability, we introduce a novel multi-vector embedding-based clustering algorithm that outperforms traditional single-vector embedding approaches while reducing indexing time by up to 14x. Furthermore, a dual-store data architecture minimizes LLM API calls, reducing both operational cost and response latency by up to approximately 3x. By effectively balancing scalability and operational efficiency, DamageScope provides a robust and practical solution for real-world damage assessment tasks.
