SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING

Junlin Han; Mehrdad Shoeiby; Tim Malthus; Elizabeth Botha; Janet Anstee; Saeed Anwar; Ran Wei; Lars Petersson; Mohammad Ali Armin

doi:10.1109/IGARSS47720.2021.9553857

SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING

Junlin Han, Mehrdad Shoeiby, Tim Malthus, Elizabeth Botha, Janet Anstee, Saeed Anwar, Ran Wei, Lars Petersson, Mohammad Ali Armin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

69 Scopus citations

Abstract

Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image translation framework. We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images. Additionally, we release a large-scale real underwater image dataset to support both paired and unpaired training modules. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method.

Original language	English
Title of host publication	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2385-2388
Number of pages	4
ISBN (Electronic)	9781665403696
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9553857
State	Published - 2021
Externally published	Yes

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2021-July

Bibliographical note

Publisher Copyright:
© 2021 IEEE

Keywords

Contrastive learning
Image-to-image translation
Underwater image dataset
Underwater image restoration

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS47720.2021.9553857

Cite this

Han, J., Shoeiby, M., Malthus, T., Botha, E., Anstee, J., Anwar, S., Wei, R., Petersson, L., & Armin, M. A. (2021). SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 2385-2388). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS47720.2021.9553857

@inproceedings{cef1342008ac4e91828f912700aa447d,

title = "SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING",

abstract = "Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image translation framework. We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images. Additionally, we release a large-scale real underwater image dataset to support both paired and unpaired training modules. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method.",

keywords = "Contrastive learning, Image-to-image translation, Underwater image dataset, Underwater image restoration",

author = "Junlin Han and Mehrdad Shoeiby and Tim Malthus and Elizabeth Botha and Janet Anstee and Saeed Anwar and Ran Wei and Lars Petersson and Armin, \{Mohammad Ali\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9553857",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2385--2388",

booktitle = "IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

address = "United States",

}

Han, J, Shoeiby, M, Malthus, T, Botha, E, Anstee, J, Anwar, S, Wei, R, Petersson, L & Armin, MA 2021, SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING. in IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2021-July, Institute of Electrical and Electronics Engineers Inc., pp. 2385-2388. https://doi.org/10.1109/IGARSS47720.2021.9553857

SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING. / Han, Junlin; Shoeiby, Mehrdad; Malthus, Tim et al.
IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2385-2388 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING

AU - Han, Junlin

AU - Shoeiby, Mehrdad

AU - Malthus, Tim

AU - Botha, Elizabeth

AU - Anstee, Janet

AU - Anwar, Saeed

AU - Wei, Ran

AU - Petersson, Lars

AU - Armin, Mohammad Ali

PY - 2021

Y1 - 2021

N2 - Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image translation framework. We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images. Additionally, we release a large-scale real underwater image dataset to support both paired and unpaired training modules. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method.

AB - Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image translation framework. We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images. Additionally, we release a large-scale real underwater image dataset to support both paired and unpaired training modules. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method.

KW - Contrastive learning

KW - Image-to-image translation

KW - Underwater image dataset

KW - Underwater image restoration

UR - https://www.scopus.com/pages/publications/85106182014

U2 - 10.1109/IGARSS47720.2021.9553857

DO - 10.1109/IGARSS47720.2021.9553857

M3 - Conference contribution

AN - SCOPUS:85106182014

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2385

EP - 2388

BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Han J, Shoeiby M, Malthus T, Botha E, Anstee J, Anwar S et al. SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 2385-2388. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS47720.2021.9553857

SINGLE UNDERWATER IMAGE RESTORATION BY CONTRASTIVE LEARNING

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this