Synergistic Perception and Generative Recomposition: A Multi-Agent Orchestration for Expert-Level Building Inspection
2026-03-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of inspecting building facade defects, which is hard because defects vary a lot, can blend into backgrounds, and often appear together. They propose FacadeFixer, a system where different specialized agents work together to detect and segment defects, while a generative agent creates realistic augmented images to improve training. This approach helps separate complex defects from noisy backgrounds and produces better data for learning. Their experiments show that FacadeFixer outperforms existing methods, especially in accurately identifying fine structural defects. They also provide a new detailed dataset to support this research.
Facade defect inspectionStructural health monitoringDetection and segmentationPixel-level annotationsData augmentationMulti-agent frameworkGenerative synthesisImage segmentationComposite defectsUrban maintenance
Authors
Hui Zhong, Yichun Gao, Luyan Liu, Xusen Guo, Zhaonian Kuang, Qiming Zhang, Xinhu Zheng
Abstract
Building facade defect inspection is fundamental to structural health monitoring and sustainable urban maintenance, yet it remains a formidable challenge due to extreme geometric variability, low contrast against complex backgrounds, and the inherent complexity of composite defects (e.g., cracks co-occurring with spalling). Such characteristics lead to severe pixel imbalance and feature ambiguity, which, coupled with the critical scarcity of high-quality pixel-level annotations, hinder the generalization of existing detection and segmentation models. To address gaps, we propose \textit{FacadeFixer}, a unified multi-agent framework that treats defect perception as a collaborative reasoning task rather than isolated recognition. Specifically,\textit{FacadeFixer} orchestrates specialized agents for detection and segmentation to handle multi-type defect interference, working in tandem with a generative agent to enable semantic recomposition. This process decouples intricate defects from noisy backgrounds and realistically synthesizes them onto diverse clean textures, generating high-fidelity augmented data with precise expert-level masks. To support this, we introduce a comprehensive multi-task dataset covering six primary facade categories with pixel-level annotations. Extensive experiments demonstrate that \textit{FacadeFixer} significantly outperforms state-of-the-art (SOTA) baselines. Specifically, it excels in capturing pixel-level structural anomalies and highlights generative synthesis as a robust solution to data scarcity in infrastructure inspection. Our code and dataset will be made publicly available.