Fractex2D — Fracture Detection
Fracture segmentation on UAV outcrop orthomosaics. The Deep Learning and Vectorize tabs run the same pipeline and the same models as the FraXtex QGIS plugin.
ONNX inference
Upload an RGB orthophoto. Models are downloaded from ayoubft/fraXteX on first use.
Patch size and input scaling are read from the model file itself. Patch overlap blends neighbouring tiles to remove seams; cost rises steeply, with 50% running about 4x the patches of 0%.
ℹ️ U-Net trained from scratch, 31 M parameters. Normalizes inside the graph with dataset statistics, and accepts any patch size that is a multiple of 16.
| RGB orthophoto | DEM — not used by the selected model | Model | Patch overlap |
|---|
Large rasters: run this on your own machine, with no size limit — either the FraXtex QGIS plugin or git clone https://huggingface.co/spaces/ayoubft/fractex2d && pip install -r requirements.txt && python app.py.
Citation
If you use this Space, the models or the FraXtex plugin in your work, please cite: Fatihi, A., Caldeira, J., Beucler, T., Thiele, S. T., & Samsu, A. (2026). Towards robust fracture mapping: benchmarking automatic fracture mapping in 2D outcrop imagery. EGUsphere [preprint]. https://doi.org/10.5194/egusphere-2026-1097
The sample images originate from: Nordbäck, N., & Ovaskainen, N. (2022). UAV-acquired orthomosaics of Loviisa shoreline outcrops (Version 1.0.0) [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.7077519