Image Restoration using Autoencoding Priors

Siavash Arjomand Bigdeli, Matthias Zwicker

2018

Abstract

We propose to leverage denoising autoencoder networks as priors to address image restoration problems. We build on the key observation that the output of an optimal denoising autoencoder is a local mean of the true data density, and the autoencoder error (the difference between the output and input of the trained autoencoder) is a mean shift vector. We use the magnitude of this mean shift vector, that is, the distance to the local mean, as the negative log likelihood of our natural image prior. For image restoration, we maximize the likelihood using gradient descent by backpropagating the autoencoder error. A key advantage of our approach is that we do not need to train separate networks for different image restoration tasks, such as non-blind deconvolution with different kernels, or super-resolution at different magnification factors. We demonstrate state of the art results for non-blind deconvolution and super-resolution using the same autoencoding prior.

Download


Paper Citation


in Harvard Style

Arjomand Bigdeli S. and Zwicker M. (2018). Image Restoration using Autoencoding Priors. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 33-44. DOI: 10.5220/0006532100330044


in Bibtex Style

@conference{visapp18,
author={Siavash Arjomand Bigdeli and Matthias Zwicker},
title={Image Restoration using Autoencoding Priors},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={33-44},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006532100330044},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Image Restoration using Autoencoding Priors
SN - 978-989-758-290-5
AU - Arjomand Bigdeli S.
AU - Zwicker M.
PY - 2018
SP - 33
EP - 44
DO - 10.5220/0006532100330044
PB - SciTePress