Share Email Print

Proceedings Paper • Open Access

Deep learning for inverse imaging problems: some recent approaches (Conference Presentation)
Author(s): Carola-Bibiane Schönlieb

Paper Abstract

In this talk we discuss the idea of data-driven regularisers for inverse imaging problems. We are in particular interested in the combination of model-based and purely data-driven image processing approaches. In this context we will make a journey from “shallow” learning for computing optimal parameters for variational regularisation models by bilevel optimization to the investigation of different approaches that use deep neural networks for solving inverse imaging problems. Alongside all approaches that are being discussed, their numerical solution and available solution guarantees will be stated.

Paper Details

Date Published: 14 March 2019
Proc. SPIE 10949, Medical Imaging 2019: Image Processing, 109490R (14 March 2019); doi: 10.1117/12.2519510
Show Author Affiliations
Carola-Bibiane Schönlieb, Univ. of Cambridge (United Kingdom)

Published in SPIE Proceedings Vol. 10949:
Medical Imaging 2019: Image Processing
Elsa D. Angelini; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?