This code allows to train a CNN model to predict a good map of penalizations for the different term of an Active Contour Model (ACM) such that the result gets close to a set of ground truth contours, as presented in [1] (to appear in CVPR 2018).

A preprint of the paper can be found in https://arxiv.org/pdf/1803.06329.pdf

Vaihingen buildings

Bing Huts

Download and unzip the datasets. Modify the dataset paths in the main files and run them with Python 3. Requires Tensorflow 1.4.

Please contact me at [email protected] for questions and feedback.

[1] Marcos, D., Tuia, D., Kellenberger, B., Zhang, L., Bai, M., Liao, R. & Urtasun, R. (2018). Learning deep structured active contours end-to-end. arXiv preprint arXiv:1803.06329.

https://github.com/siddigss/Active-Contours.git

https://github.com/siddigss/S_cubed/tree/master/Image%20Processing/Active%20Contours