Image Restoration using Plug-and-Play CNN MAP Denoisers
Siavash Bigdeli, David Honzátko, Sabine Süsstrunk, L. Andrea Dunbar
2020
Abstract
Plug-and-play denoisers can be used to perform generic image restoration tasks independent of the degradation type. These methods build on the fact that the Maximum a Posteriori (MAP) optimization can be solved using smaller sub-problems, including a MAP denoising optimization. We present the first end-to-end approach to MAP estimation for image denoising using deep neural networks. We show that our method is guaranteed to minimize the MAP denoising objective, which is then used in an optimization algorithm for generic image restoration. We provide theoretical analysis of our approach and show the quantitative performance of our method in several experiments. Our experimental results show that the proposed method can achieve 70x faster performance compared to the state-of-the-art, while maintaining the theoretical perspective of MAP.
DownloadPaper Citation
in Harvard Style
Bigdeli S., Honzátko D., Süsstrunk S. and Dunbar L. (2020). Image Restoration using Plug-and-Play CNN MAP Denoisers. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 85-92. DOI: 10.5220/0008990700850092
in Bibtex Style
@conference{visapp20,
author={Siavash Bigdeli and David Honzátko and Sabine Süsstrunk and L. Andrea Dunbar},
title={Image Restoration using Plug-and-Play CNN MAP Denoisers},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={85-92},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008990700850092},
isbn={978-989-758-402-2},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - Image Restoration using Plug-and-Play CNN MAP Denoisers
SN - 978-989-758-402-2
AU - Bigdeli S.
AU - Honzátko D.
AU - Süsstrunk S.
AU - Dunbar L.
PY - 2020
SP - 85
EP - 92
DO - 10.5220/0008990700850092
PB - SciTePress