Non-local Matching of Superpixel-based Deep Features for Color Transfer

Hernan Carrillo, Michaël Clément, Aurélie Bugeau

2022

Abstract

In this article, we propose a new method for matching high-resolution feature maps from CNNs using attention mechanisms. To avoid the quadratic scaling problem of all-to-all attention, this method relies on a superpixel-based pooling dimensionality reduction strategy. From this pooling, we efficiently compute non-local similarities between pairs of images. To illustrate the interest of these new methodological blocks, we apply them to the problem of color transfer between a target image and a reference image. While previous methods for this application can suffer from poor spatial and color coherence, our approach tackles these problems by leveraging on a robust non-local matching between high-resolution low-level features. Finally, we highlight the interest in this approach by showing promising results in comparison with state-of-the-art methods.

Paper Citation

in Harvard Style

Carrillo H., Clément M. and Bugeau A. (2022). Non-local Matching of Superpixel-based Deep Features for Color Transfer. 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 38-47. DOI: 10.5220/0010767900003124

in Bibtex Style

@conference{visapp22,
author={Hernan Carrillo and Michaël Clément and Aurélie Bugeau},
title={Non-local Matching of Superpixel-based Deep Features for Color Transfer},
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={38-47},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010767900003124},
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 - Non-local Matching of Superpixel-based Deep Features for Color Transfer
SN - 978-989-758-555-5
AU - Carrillo H.
AU - Clément M.
AU - Bugeau A.
PY - 2022
SP - 38
EP - 47
DO - 10.5220/0010767900003124
PB - SciTePress