FACS-Net: Frequency-Aware Crack Segmentation Network for Thin Cracks (Checkpoint, and Results)

Frequency-Aware Crack Segmentation Network (FACS-Net) for Thin Cracks via Topology Preservation<br>FACS-Net is a frequency-aware neural architecture designed to enhance the segmentation of ultra-thin cracks (≤2px) in civil infrastructure images. It combines a hybrid CNN-Transformer encoder with a frequency-modulated decoder and introduces a topology-aware loss function (CT-Loss) to enforce structural continuity.<br>Contents<br>🔧 Pretrained Models- `CV12K.ckpt` – trained on <b>CrackVision12K</b>- `Omni.ckpt` – trained on <b>OmniCrack30K</b><br>🖼️ Segmentation Outputs- `CrackVision12K.zip` – result images from CrackVision12K test set- `OmniCrack30K.zip` – result images from OmniCrack30K benchmark<br>📊 Evaluation- Includes metrics: IoU, CL-IoU, CTS- Use with the official codebase for inference and analysis<br>&gt; 🔗 <b>Project GitHub Repository:</b>https://github.com/SH-Joo/FACS<br>---<br><b>License:</b>All contents are released under the <b>MIT License</b>. Free to use and modify with proper attribution.<br><b>Note:</b> The associated paper is currently under review. Please cite the SSRN preprint when available.<br>

基于拓扑保持的面向细裂纹的频率感知裂纹分割网络（FACS-Net）

FACS-Net是一种频率感知型神经架构，旨在提升土木基础设施图像中超细裂纹（≤2像素）的分割精度。该架构融合了混合卷积神经网络（Convolutional Neural Network, CNN）-Transformer编码器与频率调制解码器，并引入拓扑感知损失函数（CT-Loss）以保障结构连续性。

### 内容
🔧 预训练模型
- `CV12K.ckpt` —— 在**CrackVision12K**数据集上训练所得
- `Omni.ckpt` —— 在**OmniCrack30K**数据集上训练所得

🖼️ 分割输出结果
- `CrackVision12K.zip` —— CrackVision12K测试集的分割结果图像
- `OmniCrack30K.zip` —— OmniCrack30K基准测试集的分割结果图像

📊 评估指标
- 涵盖IoU、CL-IoU、CTS三类评估指标
- 需配合官方代码库进行推理与分析

> 🔗 **项目GitHub仓库：**https://github.com/SH-Joo/FACS

---

**许可证：** 所有内容均采用**MIT许可证**发布，允许在注明原作者出处的前提下自由使用与修改。
**备注：** 相关学术论文目前处于审稿阶段，待正式发布后请引用其SSRN预印本版本。