Boosting Weakly Convex Ridge Regularizers with Spatial Adaptivity
S. Neumayer, M. Pourya, A. Goujon, M. Unser
Proceedings of the Fourth Workshop on Deep Learning and Inverse Problems (NeurIPS'23), New Orleans LA, USA, December 16, 2023.
We propose to enhance 1-weakly convex ridge regularizers for image reconstruction by incorporating spatial adaptivity. To this end, we resort to a neural network that generates a weighting mask from an initial reconstruction, which is obtained with the baseline regularizer. Empirically, the learned mask can capture long-range dependencies and leads to a smaller penalization of inherent image structures. Our experiments show that spatial adaptivity improves the performance of image denoising and MRI reconstruction.
@INPROCEEDINGS(http://bigwww.epfl.ch/publications/neumayer2305.html,
AUTHOR="Neumayer, S. and Pourya, M. and Goujon, A. and Unser, M.",
TITLE="Boosting Weakly Convex Ridge Regularizers with Spatial
Adaptivity",
BOOKTITLE="Proceedings of the Fourth Workshop on Deep Learning and
Inverse Problems ({NeurIPS'23})",
YEAR="2023",
editor="",
volume="",
series="",
pages="1--10",
address="New Orleans LA, USA",
month="December 16,",
organization="",
publisher="",
note="")
© 2023 NeurIPS. Personal use of this material is permitted. However, permission to
reprint/republish this material for advertising or promotional purposes or for creating
new collective works for resale or redistribution to servers or lists, or to reuse any
copyrighted component of this work in other works must be obtained from NeurIPS.
This material is presented to ensure timely dissemination of scholarly and technical work.
Copyright and all rights therein are retained by authors or by other copyright holders.
All persons copying this information are expected to adhere to the terms and constraints
invoked by each author's copyright. In most cases, these works may not be reposted without
the explicit permission of the copyright holder.