deformation-inversion-layer 1.1.0

Deformation inversion layer is a neural network layer for inverting deformation fields

Deformation inversion layer

Deformation inversion layer is a neural network layer for inverting deformation fields develped as part of SITReg, a deep learning intra-modality image registration arhitecture fulfilling strict symmetry properties.

Installation

Install using pip by running the command

pip install deformation-inversion-layer

Requirements

• Python 3.6+
• PyTorch 1.10+

Source code

Code repository can be found at GitHub https://github.com/honkamj/deformation-inversion-layer

Documentation

For documentation, see the GitHub repository.

Publication

If you use deformation inversion layer, please cite the SITReg paper. Details for citing can be found at the GitHub repository.

Acknowledgments

Tutorial by Zico Kolter, David Duvenaud, and Matt Johnson was very helpful in implementing the layer.

License

Deformation inversion layer is released under the MIT license.