CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917430935158784 |
|---|---|
| author | Sadallah, Nassim Allili, Mohand Saïd |
| author_facet | Sadallah, Nassim Allili, Mohand Saïd |
| contents | Reliable crack detection and segmentation are vital for structural health monitoring, yet the scarcity of well-annotated data constitutes a major challenge. To address this limitation, we propose a novel context-aware generative framework designed to synthesize realistic crack growth patterns for data augmentation. Unlike existing methods that primarily manipulate textures or background content, CrackForward explicitly models crack morphology by combining directional crack elongation with learned thickening and branching. Our framework integrates two key innovations: (i) a contextually guided crack expansion module, which uses local directional cues and adaptive random walk to simulate realistic propagation paths; and (ii) a two-stage U-Net-style generator that learns to reproduce spatially varying crack characteristics such as thickness, branching, and growth. Experimental results show that the generated samples preserve target-stage saturation and thickness characteristics and improve the performance of several crack segmentation architectures. These results indicate that structure-aware synthetic crack generation can provide more informative training data than conventional augmentation alone. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19941 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation Sadallah, Nassim Allili, Mohand Saïd Computer Vision and Pattern Recognition Reliable crack detection and segmentation are vital for structural health monitoring, yet the scarcity of well-annotated data constitutes a major challenge. To address this limitation, we propose a novel context-aware generative framework designed to synthesize realistic crack growth patterns for data augmentation. Unlike existing methods that primarily manipulate textures or background content, CrackForward explicitly models crack morphology by combining directional crack elongation with learned thickening and branching. Our framework integrates two key innovations: (i) a contextually guided crack expansion module, which uses local directional cues and adaptive random walk to simulate realistic propagation paths; and (ii) a two-stage U-Net-style generator that learns to reproduce spatially varying crack characteristics such as thickness, branching, and growth. Experimental results show that the generated samples preserve target-stage saturation and thickness characteristics and improve the performance of several crack segmentation architectures. These results indicate that structure-aware synthetic crack generation can provide more informative training data than conventional augmentation alone. |
| title | CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.19941 |