.png){kind=icon}
.png){kind=icon}
Return
DiffCrack: A semantic–structural controllable framework for crack image generation in complex scenes
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113771.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A diffusion-based framework with decoupled geometry and semantics for crack generation. • A hierarchical prompt attention mechanism enables attribute-specific visual modulation. • The generated dataset significantly improves segmentation accuracy in complex scenes. • A mask pre-processing pipeline ensures geometric plausibility and spatial alignment. • Quantitative and visual results demonstrate superior fidelity over state-of-the-art methods.
Keywords:
Image generation
Pavement cracks
Diffusion model
Data enhancement
Multimodal data
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
View more organizations