# CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation

arXiv: https://arxiv.org/abs/2604.19941 · HTML: https://mlsanity.com/paper/2604.19941/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [Expanding Small-Scale Datasets with Guided Imagination](https://mlsanity.com/paper/2211.13976/) (2022)
- [Semantic Image Synthesis via Class-Adaptive Cross-Attention](https://mlsanity.com/paper/2308.16071/) (2023)

## Abstract (arXiv)

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.