Skip to main content

Andreas Hauptmann

Scholar in residence March, May and September – November 2024

Andreas Hauptmann holds a position as Academy Research Fellow and Associate Professor of Computational Mathematics at the Research Unit of Mathematical Sciences, University of Oulu, and as Honorary Associate Professor at the Department of Computer Science, University College London. He also represents the Centre of Excellence of Inverse Modelling and Imaging (2018-2025) as a partner PI at the University of Oulu as well as the Flagship of Advanced Mathematics for Sensing, Imaging and Modelling (FAME) funded by the Research Council of Finland (2024-2031). His research interest is in inverse problems and tomographic imaging, focusing on combining model-based inversion techniques with data-driven methods. His work concentrates on applications in medical image reconstruction, such as Computed tomography and magnetic resonance tomography, as well as fundamental theoretical work to understand the developed methodology.

During his stay, he will expand an active collaboration with Prof. Ozan Öktem and members of the Division for Mathematics, a group for Numerics, Optimization & Systems. Together with his host, Andreas will work on combining classical mathematically well-understood variational methods for inverse problems with recent data-driven approaches. This gives rise to a framework usually referred to as learned image reconstruction. A primary part of this work concentrates on translating the rich theory of model-based inversion to the data-driven world. This enables a deeper understanding of data-driven methods and challenges the often-raised concern of the black-box nature of the data-driven world.

Andreas looks forward to discussing applications of data-driven methods and their combination with model-based techniques with members of Digital Futures, students and faculty at KTH.



Ozan Öktem

Associate Professor at KTH, Co-PI of project Spatiotemporal reconstruction with learned deformations for earlier cancer detection via PET imaging, Member of the Strategic Research Committee, Digital Futures Faculty