755 citations · 1.6k across the 34 of their papers we have counts for
6 papers · 1 filter
Neural incomplete factorization: learning preconditioners for the conjugate gradient method
Paul Häusner, Ozan Öktem, Jens Sjölund
The convergence of the conjugate gradient method for solving large-scale and sparse linear equation systems depends on the spectral properties of the system matrix, which can be im…
Regularising orientation estimation in Cryo-EM 3D map refinement through measure-based lifting over Riemannian manifolds
Willem Diepeveen, Jan Lellmann, Ozan Öktem +1
Motivated by the trade-off between noise-robustness and data-consistency for joint 3D map reconstruction and rotation estimation in single particle cryogenic-electron microscopy (C…
Accelerated Forward-Backward Optimization using Deep Learning
Sebastian Banert, Jevgenija Rudzusika, Ozan Öktem +1
We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, bu…
Template-Based Image Reconstruction from Sparse Tomographic Data
Lukas F. Lang, Sebastian Neumayer, Ozan Öktem +1
We propose a variational regularisation approach for the problem of template-based image reconstruction from indirect, noisy measurements as given, for instance, in X-ray computed…
Learned Primal-dual Reconstruction
Jonas Adler, Ozan Öktem
We propose the Learned Primal-Dual algorithm for tomographic reconstruction. The algorithm accounts for a (possibly non-linear) forward operator in a deep neural network by unrolli…
Solving ill-posed inverse problems using iterative deep neural networks
Jonas Adler, Ozan Öktem
We propose a partially learned approach for the solution of ill posed inverse problems with not necessarily linear forward operators. The method builds on ideas from classical regu…