.png){kind=icon}
.png){kind=icon}
Return
A versatile synthetic data generation framework for crack detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engstruct.2025.121428.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• CrackGen combines Stable Diffusion and ControlNet for realistic synthetic cracks. • Simultaneous image and label generation removes the need for manual annotation. • Controlled prompts allow full customization of backgrounds and crack properties. • RRT-based crack sketches yield fractal-like patterns mirroring real crack growth. • Purely synthetic data from CrackGen matches real detection performance.
Keywords:
Crack detection
Data generation
Stable diffusion
ControlNet
Infrastructure inspection
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.4
Papers:
2.1W
Citations:
8.7W