Adaptive Mesh Refinement for Nonparametric Image Registration

3D image registration is a computationally extensive problem which is commonly solved in medical imaging. The complexity of the problem stems from its size and non-linearity. In this paper we present an approach that drastically reduces the problem size by using adaptive mesh refinement. Our approach requires special and careful discretization of the variational form on adaptive octree grids. It further requires an appropriate refinement criteria. We show that this approach can reduce the computational time in a factor of 10 or so compared to the non-adaptive approach.