Coarse-to-fine crack cue for robust crack detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915405505757184 |
|---|---|
| author | Liu, Zelong Gu, Yuliang Sun, Zhichao Zhu, Huachao Xiao, Xin Du, Bo Najman, Laurent Xu, Yongchao |
| author_facet | Liu, Zelong Gu, Yuliang Sun, Zhichao Zhu, Huachao Xiao, Xin Du, Bo Najman, Laurent Xu, Yongchao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16851 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Coarse-to-fine crack cue for robust crack detection Liu, Zelong Gu, Yuliang Sun, Zhichao Zhu, Huachao Xiao, Xin Du, Bo Najman, Laurent Xu, Yongchao Computer Vision and Pattern Recognition Neural and Evolutionary Computing Image and Video Processing 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. |
| title | Coarse-to-fine crack cue for robust crack detection |
| topic | Computer Vision and Pattern Recognition Neural and Evolutionary Computing Image and Video Processing |
| url | https://arxiv.org/abs/2507.16851 |