Deep ContourFLow

In This repository you can find the code for both: unsupervised Deep-ContourFlow and One shot learning Deep-ContourFlow.

if you use the the code please cite the following paper:

@misc{habis2024deepcontourflowadvancingactive,
      title={Deep ContourFlow: Advancing Active Contours with Deep Learning}, 
      author={Antoine Habis and Vannary Meas-Yedid and Elsa Angelini and Jean-Christophe Olivo-Marin},
      year={2024},
      eprint={2407.10696},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.10696}, 
}

To use this repository please first install torch-contour:

$pip install torch_contour>=1.3.0

Unsupervised Deep ContourFLow:

To use Unsupervised DCF just add your image in images_test and run the algorithm using the notebook: unsupervised_dcf.ipynb

One shot learning: Application on Dilated Tubules

To use the one shot version of the algorithm please provide a support image with a support mask and a query image in images_test and run the algorithm using one_shot_dcf.ipynb.