Coarse-to-fine crack cue for robust crack detection

2025-07-21

AI Summary

Weak cross-domain generalization and neglect of crack elongation characteristics hinder existing crack detection models. To address this, we propose a structure-aware coarse-to-fine crack cue generation method leveraging geometric priors. Specifically, we exploit the thin, elongated nature of cracks for the first time: maximum pooling followed by upsampling constructs a coarse crack-free background; a reconstruction network refines this background; and subsequent differencing yields highly discriminative crack cues. The proposed module is plug-and-play and seamlessly integrates into mainstream detection frameworks. Extensive experiments on multiple benchmark datasets demonstrate consistent performance gains across three state-of-the-art models—particularly notable under cross-domain settings, where robustness and stability improve substantially. Our approach establishes a new paradigm for structure-aware generic crack detection.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Feature Construction/Reformulation
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Crack detection is an important task in computer vision. Despite impressive in-dataset performance, deep learning-based methods still struggle in generalizing to unseen domains. The thin structure property of cracks is usually overlooked by previous methods. In this work, we introduce CrackCue, a novel method for robust crack detection based on coarse-to-fine crack cue generation. The core concept lies on leveraging the thin structure property to generate a robust crack cue, guiding the crack detection. Specifically, we first employ a simple max-pooling and upsampling operation on the crack image. This results in a coarse crack-free background, based on which a fine crack-free background can be obtained via a reconstruction network. The difference between the original image and fine crack-free background provides a fine crack cue. This fine cue embeds robust crack prior information which is unaffected by complex backgrounds, shadow, and varied lighting. As a plug-and-play method, we incorporate the proposed CrackCue into three advanced crack detection networks. Extensive experimental results demonstrate that the proposed CrackCue significantly improves the generalization ability and robustness of the baseline methods. The source code will be publicly available.

Problem

• Improves crack detection generalization across unseen domains
• Leverages thin structure property for robust crack cues
• Addresses challenges from complex backgrounds and lighting variations

Innovation

• Coarse-to-fine crack cue generation
• Max-pooling and upsampling operations
• Plug-and-play reconstruction network integration