An Effective 3D ResNet Architecture for Stereo Image Retrieval

E. Ghodhbani, M. Kaaniche, A. Benazza-Benyahia

2021

Abstract

While recent stereo images retrieval techniques have been developed based mainly on statistical approaches, this work aims to investigate deep learning ones. More precisely, our contribution consists in designing a two-branch neural networks to extract deep features from the stereo pair. In this respect, a 3D residual network architecture is first employed to exploit the high correlation existing in the stereo pair. This 3D model is then combined with a 2D one applied to the disparity maps, resulting in deep feature representations of the texture information as well as the depth one. Our experiments, carried out on a large scale stereo image dataset, have shown the good performance of the proposed approach compared to the state-of-the-art methods.

Paper Citation

in Harvard Style

Ghodhbani E., Kaaniche M. and Benazza-Benyahia A. (2021). An Effective 3D ResNet Architecture for Stereo Image Retrieval. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 380-387. DOI: 10.5220/0010261103800387

in Bibtex Style

@conference{visapp21,
author={E. Ghodhbani and M. Kaaniche and A. Benazza-Benyahia},
title={An Effective 3D ResNet Architecture for Stereo Image Retrieval},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={380-387},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010261103800387},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - An Effective 3D ResNet Architecture for Stereo Image Retrieval
SN - 978-989-758-488-6
AU - Ghodhbani E.
AU - Kaaniche M.
AU - Benazza-Benyahia A.
PY - 2021
SP - 380
EP - 387
DO - 10.5220/0010261103800387
PB - SciTePress