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>