Adversarial Regularizers in Inverse Problems
Abstract
Inverse Problems in medical imaging and computer vision are traditionally solved using purely model-based methods. Among those variational regularization models are one of the most popular approaches. We propose a new framework for applying data-driven approaches to inverse problems, using a neural network as a regularization functional. The network learns to discriminate between the distribution of ground truth images and the distribution of unregularized reconstructions. Once trained, the network is applied to the inverse problem by solving the corresponding variational problem. Unlike other data-based approaches for inverse problems, the algorithm can be applied even if only unsupervised training data is available. Experiments demonstrate the potential of the framework for denoising on the BSDS dataset and for computer tomography reconstruction on the LIDC dataset.
Cite
Text
Lunz et al. "Adversarial Regularizers in Inverse Problems." Neural Information Processing Systems, 2018.Markdown
[Lunz et al. "Adversarial Regularizers in Inverse Problems." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/lunz2018neurips-adversarial/)BibTeX
@inproceedings{lunz2018neurips-adversarial,
title = {{Adversarial Regularizers in Inverse Problems}},
author = {Lunz, Sebastian and Öktem, Ozan and Schönlieb, Carola-Bibiane},
booktitle = {Neural Information Processing Systems},
year = {2018},
pages = {8507-8516},
url = {https://mlanthology.org/neurips/2018/lunz2018neurips-adversarial/}
}