Metamorphic image registration using a semi-Lagrangian scheme
This work addresses image registration for medical imaging or computer vision, presenting an incremental improvement in stability and computational efficiency.
The paper tackled image registration by implementing LDDMM and Metamorphosis using a semi-Lagrangian scheme for geodesic shooting, showing that this approach is more stable than a standard Eulerian scheme and providing a GPU implementation in PyTorch for acceleration.
In this paper, we propose an implementation of both Large Deformation Diffeomorphic Metric Mapping (LDDMM) and Metamorphosis image registration using a semi-Lagrangian scheme for geodesic shooting. We propose to solve both problems as an inexact matching providing a single and unifying cost function. We demonstrate that for image registration the use of a semi-Lagrangian scheme is more stable than a standard Eulerian scheme. Our GPU implementation is based on PyTorch, which greatly simplifies and accelerates the computations thanks to its powerful automatic differentiation engine. It will be freely available at https://github.com/antonfrancois/Demeter_metamorphosis.