DIRECT is the Deep Image REConstruction Toolkit that implements state-of-the-art inverse problem solvers. It includes inverse problem solvers such as the Learned Primal Dual algorithm and Recurrent Inference Machine, which were part of the winning solution in Facebook & NYUs FastMRI challenge in 2019 and the Calgary-Campinas MRI reconstruction challenge at MIDL 2020.

See install.md.

See getting_started.md, check out the documentation. In the projects folder examples are given on how to train models on public datasets.

We provide a set of baseline results and trained models in the DIRECT Model Zoo.

DIRECT is released under the Apache 2.0 License.

If you use DIRECT in your own research, or want to refer to baseline results published in the DIRECT Model Zoo, please use the following BiBTeX entry:

@misc{DIRECTTOOLKIT,
  author =       {Jonas Teuwen, Nikita Moriakov, Dimitrios Karkalousos, Matthan Caan},
  title =        {DIRECT},
  howpublished = {\url{https://github.com/directgroup/direct}},
  year =         {2020}
}