PuSH - Publikationsserver des Helmholtz Zentrums München

Ortega, J.V. ; Haas, M.* ; Effland, A.*

Learning Diffusion Functions for Image Restoration.

In: (Proceedings - International Symposium on Biomedical Imaging). 345 E 47th St, New York, Ny 10017 Usa: Ieee, 2024. DOI: 10.1109/ISBI56570.2024.10635306 (Proceedings - International Symposium on Biomedical Imaging)
Verlagsversion DOI
Anisotropic diffusion models play a major role in numerous image restoration tasks. A key ingredient for these models is the diffusion function, which is normally an a priori fixed function. In this paper, we advocate a novel approach to learning the diffusion function, which is represented as a Fields of Experts (FoE) function or a U-Net. In several numerical experiments, we prove our technique outperforms both the classical models and state-of-the-art algorithms. The generalization to other datasets/restoration problems is also discussed.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Anisotropic Diffusion
ISSN (print) / ISBN 1945-7928
e-ISSN 1945-8452
Konferenztitel Proceedings - International Symposium on Biomedical Imaging
Verlag Ieee
Verlagsort 345 E 47th St, New York, Ny 10017 Usa
Institut(e) Helmholtz Pioneer Campus (HPC)
Förderungen German Research Foundation under Germany's Excellence Strategy