Variational Networks: An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Abstract

We investigate a well-known phenomenon of variational approaches in image processing, where typically the best image quality is achieved when the gradient flow process is stopped before converging to a stationary point. This paradox originates from a tradeoff between optimization and modelling errors of the underlying variational model and holds true even if deep learning methods are used to learn highly expressive regularizers from data. In this paper, we take advantage of this paradox and introduce an optimal stopping time into the gradient flow process, which in turn is learned from data by means of an optimal control approach. As a result, we obtain highly efficient numerical schemes that achieve competitive results for image denoising and image deblurring. A nonlinear spectral analysis of the gradient of the learned regularizer gives enlightening insights about the different regularization properties.
Originalspracheenglisch
Seiten (von - bis)396-416
FachzeitschriftJournal of Mathematical Imaging and Vision
Jahrgang62
DOIs
PublikationsstatusVeröffentlicht - 11 Mär 2020

Fingerprint Untersuchen Sie die Forschungsthemen von „Variational Networks: An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration“. Zusammen bilden sie einen einzigartigen Fingerprint.

  • Dieses zitieren