Keynote speaker

Thomas Pock

TU Graz, Austria

Thomas Pock, received his MSc (1998-2004) and his PhD (2005-2008) in Computer Engineering (Telematik) from Graz University of Technology. After a Post-doc position at the University of Bonn, he moved back to Graz University of Technology where he has been an Assistant Professor at the Institute for Computer Graphics and Vision. In 2013 Thomas Pock received the START price of the Austrian Science Fund (FWF) and the German Pattern recognition award of the German association for pattern recognition (DAGM) and in 2014, Thomas Pock received an starting grant from the European Research Council (ERC). Since June 2014, Thomas Pock is a Professor of Computer Science at Graz University of Technology. The focus of his research is the development of mathematical models for computer vision and image processing as well as the development of efficient convex and non-smooth optimization algorithms.

Learning better models for imaging

In this talk I will present our ongoing activities to learn better models for inverse problems in imaging. We begin by considering classical variational approaches to inverse problems, but generalize these models by introducing a large number of free model parameters. We learn these model parameters from data using supervised learning techniques. To interpret what we have learned, we perform a nonlinear eigenvalue analysis that eventually reveals interesting properties about the regularization properties of the learned models. We show applications for various inverse problems in imaging, with special emphasis on image reconstruction from undersampled MRI data.