no code implementations • 17 Dec 2018 • Daniel Budelmann, Lars König, Nils Papenberg, Jan Lellmann
We present a highly parallel method for accurate and efficient variational deformable 3D image registration on a consumer-grade graphics processing unit (GPU).
no code implementations • 27 Apr 2018 • Lars König, Jan Rühaak, Alexander Derksen, Jan Lellmann
Based on this analysis, we derive equivalent matrix-free closed-form expressions for derivative computations, eliminating the need for storing intermediate results and the costs of sparse matrix arithmetic.