This is the official code for "Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond"
Python >= 3.5.5, PyTorch == 0.3.1, torchvision == 0.2.0
Note: PyTorch 0.4 is not supported at this moment and would lead to OOM.
The easiest way to get started is to evaluate our trained models, run
python test.py
If you find our work useful in your research please consider citing our paper:
@article{abs-2004-14557,
author = {Risheng Liu and Zi Li and Xin Fan and Chenying Zhao and Hao Huang and Zhongxuan Luo},
title = {Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond},
journal = {CoRR},
volume = {abs/2004.14557},
year = {2020}
}