755 citations · 1.6k across the 34 of their papers we have counts for
10 papers · 1 filter
Learned iterative networks: An operator learning perspective
Andreas Hauptmann, Ozan Öktem
Learned image reconstruction has become a pillar in computational imaging and inverse problems. Among the most successful approaches are learned iterative networks, which are formu…
Improving the Generalisation of Learned Reconstruction Frameworks
Emilien Valat, Ozan Öktem
Ensuring proper generalization is a critical challenge in applying data-driven methods for solving inverse problems in imaging, as neural networks reconstructing an image must perf…
Self-Supervised Denoiser Framework
Emilien Valat, Andreas Hauptmann, Ozan Öktem
Reconstructing images using Computed Tomography (CT) in an industrial context leads to specific challenges that differ from those encountered in other areas, such as clinical CT. I…
Spectral decomposition of atomic structures in heterogeneous cryo-EM
Carlos Esteve-Yagüe, Willem Diepeveen, Ozan Öktem +1
We consider the problem of recovering the three-dimensional atomic structure of a flexible macromolecule from a heterogeneous cryo-EM dataset. The dataset contains noisy tomographi…
3D helical CT Reconstruction with a Memory Efficient Learned Primal-Dual Architecture
Jevgenija Rudzusika, Buda Bajić, Thomas Koehler +1
Deep learning based computed tomography (CT) reconstruction has demonstrated outstanding performance on simulated 2D low-dose CT data. This applies in particular to domain adapted…
Image reconstruction in dynamic inverse problems with temporal models
Andreas Hauptmann, Ozan Öktem, Carola Schönlieb
The paper surveys variational approaches for image reconstruction in dynamic inverse problems. Emphasis is on methods that rely on parametrised temporal models. These are here enco…