Polarimetric image recovery method with domain-adversarial learning for underwater imaging

Abstract Underwater imaging is significant but the images are always subject to degradation, which varies in different underwater environments. Factors such as light scattering, absorption, and environmental noise can affect the quality of underwater images, leading to issues such as color shift, lo...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei Tian, Jiuming Xue, Zhedong Shi, Hongling Luo, Wanyuan Cai, Wei Tao
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-86529-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832571858160975872
author Fei Tian
Jiuming Xue
Zhedong Shi
Hongling Luo
Wanyuan Cai
Wei Tao
author_facet Fei Tian
Jiuming Xue
Zhedong Shi
Hongling Luo
Wanyuan Cai
Wei Tao
author_sort Fei Tian
collection DOAJ
description Abstract Underwater imaging is significant but the images are always subject to degradation, which varies in different underwater environments. Factors such as light scattering, absorption, and environmental noise can affect the quality of underwater images, leading to issues such as color shift, low contrast, and low definition. Polarization information benefits image recovery, and existing learning-based polarimetric imaging methods ignore multiple water types (viewed as domains) and domain generalization. In this paper, we collect, to the best of our knowledge, the richest polarization color image dataset with different water types and present a specially designed neural network UPD-Net firstly employing the domain-adversarial learning strategy to recover the degraded color images. The designed water-type classifier and domain-adversarial learning strategy enable the multi-encoder to output domain-independent features, the decoder outputs clear images consistent with the ground truths with the help of the discriminator and generative-adversarial learning strategy, and there is another decoder responsible for outputting DoLP image. Comparison experiments demonstrate that our method is state-of-the-art in terms of visual effect and value metrics and that it has a strong recovery ability in the source and unseen domains, including in water with high turbidity. The proposed approach has significant potential for underwater imaging and recognition applications in varied underwater environments.
format Article
id doaj-art-64f083610a5149d78e0fe5860893c2ae
institution Kabale University
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-64f083610a5149d78e0fe5860893c2ae2025-02-02T12:15:41ZengNature PortfolioScientific Reports2045-23222025-01-0115111210.1038/s41598-025-86529-3Polarimetric image recovery method with domain-adversarial learning for underwater imagingFei Tian0Jiuming Xue1Zhedong Shi2Hongling Luo3Wanyuan Cai4Wei Tao5School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong UniversityShanghai Institute of Satellite EngineeringShanghai Institute of Satellite EngineeringSchool of Electronic Information and Electrical Engineering, Shanghai Jiao Tong UniversitySchool of Electronic Information and Electrical Engineering, Shanghai Jiao Tong UniversitySchool of Electronic Information and Electrical Engineering, Shanghai Jiao Tong UniversityAbstract Underwater imaging is significant but the images are always subject to degradation, which varies in different underwater environments. Factors such as light scattering, absorption, and environmental noise can affect the quality of underwater images, leading to issues such as color shift, low contrast, and low definition. Polarization information benefits image recovery, and existing learning-based polarimetric imaging methods ignore multiple water types (viewed as domains) and domain generalization. In this paper, we collect, to the best of our knowledge, the richest polarization color image dataset with different water types and present a specially designed neural network UPD-Net firstly employing the domain-adversarial learning strategy to recover the degraded color images. The designed water-type classifier and domain-adversarial learning strategy enable the multi-encoder to output domain-independent features, the decoder outputs clear images consistent with the ground truths with the help of the discriminator and generative-adversarial learning strategy, and there is another decoder responsible for outputting DoLP image. Comparison experiments demonstrate that our method is state-of-the-art in terms of visual effect and value metrics and that it has a strong recovery ability in the source and unseen domains, including in water with high turbidity. The proposed approach has significant potential for underwater imaging and recognition applications in varied underwater environments.https://doi.org/10.1038/s41598-025-86529-3
spellingShingle Fei Tian
Jiuming Xue
Zhedong Shi
Hongling Luo
Wanyuan Cai
Wei Tao
Polarimetric image recovery method with domain-adversarial learning for underwater imaging
Scientific Reports
title Polarimetric image recovery method with domain-adversarial learning for underwater imaging
title_full Polarimetric image recovery method with domain-adversarial learning for underwater imaging
title_fullStr Polarimetric image recovery method with domain-adversarial learning for underwater imaging
title_full_unstemmed Polarimetric image recovery method with domain-adversarial learning for underwater imaging
title_short Polarimetric image recovery method with domain-adversarial learning for underwater imaging
title_sort polarimetric image recovery method with domain adversarial learning for underwater imaging
url https://doi.org/10.1038/s41598-025-86529-3
work_keys_str_mv AT feitian polarimetricimagerecoverymethodwithdomainadversariallearningforunderwaterimaging
AT jiumingxue polarimetricimagerecoverymethodwithdomainadversariallearningforunderwaterimaging
AT zhedongshi polarimetricimagerecoverymethodwithdomainadversariallearningforunderwaterimaging
AT honglingluo polarimetricimagerecoverymethodwithdomainadversariallearningforunderwaterimaging
AT wanyuancai polarimetricimagerecoverymethodwithdomainadversariallearningforunderwaterimaging
AT weitao polarimetricimagerecoverymethodwithdomainadversariallearningforunderwaterimaging