Can We Use Neural Regularization to Solve Depth Super-resolution?

Milena Gazdieva, Oleg Voynov, Alexey Artemov, Youyi Zheng, Luiz Velho, Evgeny Burnaev

2022

Abstract

Depth maps captured with commodity sensors often require super-resolution to be used in applications. In this work we study a super-resolution approach based on a variational problem statement with Tikhonov regularization where the regularizer is parametrized with a deep neural network. This approach was previously applied successfully in photoacoustic tomography. We experimentally show that its application to depth map super-resolution is difficult, and provide suggestions about the reasons for that.

Paper Citation

in Harvard Style

Gazdieva M., Voynov O., Artemov A., Zheng Y., Velho L. and Burnaev E. (2022). Can We Use Neural Regularization to Solve Depth Super-resolution?. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 582-590. DOI: 10.5220/0010883500003124

in Bibtex Style

@conference{visapp22,
author={Milena Gazdieva and Oleg Voynov and Alexey Artemov and Youyi Zheng and Luiz Velho and Evgeny Burnaev},
title={Can We Use Neural Regularization to Solve Depth Super-resolution?},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={582-590},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010883500003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Can We Use Neural Regularization to Solve Depth Super-resolution?
SN - 978-989-758-555-5
AU - Gazdieva M.
AU - Voynov O.
AU - Artemov A.
AU - Zheng Y.
AU - Velho L.
AU - Burnaev E.
PY - 2022
SP - 582
EP - 590
DO - 10.5220/0010883500003124
PB - SciTePress