Teaching Unit 3 : Prior learning for solving inverse problems

Lecturer:  Prof. Thomas Pock

This teaching unit introduces a computational "toolbox" for learning priors in the context of solving Bayesian inverse problems in imaging. The tools covered include methods for learning optimal discretizations of total-variation related regularization terms, explicit diffusion models based on products of 1D Gaussian mixture models, and the application of the maximum entropy principle for learning generative priors.