Learning Energy-Based Models for Image Reconstruction
Speaker: Prof. Dr. Alexander Effland
Affiliation: University of Bonn, Germany
Organized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany)
ATTENDING THIS TALK
Meeting ID: 615 2629 5822 | PIN code: 150498
Abstract. Various problems in computer vision and medical imaging can be cast as inverse problems.
A frequent method for solving inverse problems is the variational approach, which amounts to minimizing an energy composed of a data fidelity term and a regularizer.
Classically, handcrafted regularizers are used, which are commonly outperformed by state-of-the-art deep learning approaches.
In this talk, we combine the variational formulation of inverse problems with deep learning by introducing the data-driven general-purpose total deep variation regularizer.
Moreover, we introduce the novel concept of shared prior learning to account for training in the absence of ground truth images.
We achieve state-of-the-art results for several imaging tasks.