Abstract
Diverse inverse problems in imaging can be cast as variational problems composed of a task-specific data fidelity term and a regularization term. In this paper, we propose a novel learnable general-purpose regularizer exploiting recent architectural design patterns from deep learning. We cast the learning problem as a discrete sampled optimal control problem, for which we derive the adjoint state equations and an optimality condition. By exploiting the variational structure of our approach, we perform a sensitivity analysis with respect to the learned parameters obtained from different training datasets. Moreover, we carry out a nonlinear eigenfunction analysis, which reveals interesting properties of the learned regularizer. We show state-of-the-art performance for classical image restoration and medical image reconstruction problems.
Originalsprache | englisch |
---|---|
Seiten | 7546-7555 |
Seitenumfang | 10 |
DOIs | |
Publikationsstatus | Veröffentlicht - 5 Aug. 2020 |
Veranstaltung | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2020 - virtuell, Virtual, USA / Vereinigte Staaten Dauer: 14 Juni 2020 → 19 Juni 2020 |
Konferenz
Konferenz | 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
---|---|
Kurztitel | CVPR 2020 |
Land/Gebiet | USA / Vereinigte Staaten |
Ort | Virtual |
Zeitraum | 14/06/20 → 19/06/20 |
ASJC Scopus subject areas
- Software
- Maschinelles Sehen und Mustererkennung