U<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si1.svg"><mml:msup><mml:mrow/><mml:mn>2</mml:mn></mml:msup></mml:math>R-pGAN: Unpaired underwater-image recovery with polarimetric generative adversarial network

Qi, Pengfei; Li, Xiaobo; Han, Yilin; Zhang, Liping; Xu, Jianuo; Cheng, Zhenzhou; Liu, Tiegen; Zhai, Jingsheng; Hu, Haofeng

doi:10.1016/j.optlaseng.2022.107112

Cited by 27 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of course, some models can achieve this function in an unsupervised way, such as the GAN network, but the performance of these methods is limited and always significantly worse than the performance of supervised methods. How to further enhance, especially by adding prior physical knowledge into training, the performance of unsupervised solutions is a burning problem [64,227].…”

Section: Discussionmentioning

confidence: 99%

“…In 2022, to break the dependence on strictly paired images, Ref. [64] proposed an unsupervised polarimetric GAN for underwater-image recovery, and merged polarization losses into the network to boost details restoration. Results (as shown in Figure 17) demonstrate that it improves the PSNR value by an average of 3.4 dB, verifying the effectiveness and superiority in different imaging conditions.…”

Section: Dehazingmentioning

confidence: 99%

“…Figure 29. Chronological evolution of the reviewed works.The references mentioned here are chronologically listed as 2014 [287], 2015 [188,189], 2016 [181,291], 2017 [52,184,278,304], 2018 [92,199,206,235,292,295], 2019 [70,91,97,140,212,221,225,234,236], 2020 [11,58,82,[173][174][175]222,273,303,305], 2021 [226,244,282,297], 2022 [22,64,211,227,231,258,259,294,306], and 2023 [210,…”

Section: Othersmentioning

confidence: 99%

“…However, PI could suffer from lower image quality, coming from hazy or cloudy effects [6,58,59], complex noise sources [60][61][62][63][64], reduced-resolution or contrast [30,[65][66][67][68], as shown in Figure 1, due to limitations of optical systems and particularities of application scenarios. This may significantly affect PI's application effects, especially in complex conditions and environments [43,69,70].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Polarimetric Imaging via Deep Learning: A Review

Liu

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Polarization can provide information largely uncorrelated with the spectrum and intensity. Therefore, polarimetric imaging (PI) techniques have significant advantages in many fields, e.g., ocean observation, remote sensing (RS), biomedical diagnosis, and autonomous vehicles. Recently, with the increasing amount of data and the rapid development of physical models, deep learning (DL) and its related technique have become an irreplaceable solution for solving various tasks and breaking the limitations of traditional methods. PI and DL have been combined successfully to provide brand-new solutions to many practical applications. This review briefly introduces PI and DL’s most relevant concepts and models. It then shows how DL has been applied for PI tasks, including image restoration, object detection, image fusion, scene classification, and resolution improvement. The review covers the state-of-the-art works combining PI with DL algorithms and recommends some potential future research directions. We hope that the present work will be helpful for researchers in the fields of both optical imaging and RS, and that it will stimulate more ideas in this exciting research field.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Dehazingmentioning

confidence: 99%

Section: Othersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Polarimetric Imaging via Deep Learning: A Review

Liu

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep-learning-based P-lidar techniques: Deep learning technology, with its nonlinear convolution operations and powerful implicit correlation learning, leverages the advantages of data-driven approaches to enhance performance in various tasks related to polarization or lidar [204][205][206][207][208][209]. Compared to traditional intensity-based lidar, P-lidar offers additional information, including time-of-flight data and polarization information.…”

Section: Discussionmentioning

confidence: 99%

Polarization Lidar: Principles and Applications

Liu,

Zhang,

Zhai

et al. 2023

Photonics

Self Cite

View full text Add to dashboard Cite

Traditional lidar techniques mainly rely on the backscattering/echo light intensity and spectrum as information sources. In contrast, polarization lidar (P-lidar) expands the dimensions of detection by utilizing the physical property of polarization. By incorporating parameters such as polarization degree, polarization angle, and ellipticity, P-lidar enhances the richness of physical information obtained from target objects, providing advantages for subsequent information analysis. Over the past five decades, the application fields of P-lidar have rapidly expanded, starting from its early use in atmospheric remote sensing to later applications in oceanic remote sensing. This review first provides a brief introduction to the basic principles of both polarization and P-lidar, along with typical systems. It then explores the applications of P-lidar in various remote sensing fields, including atmospheric, oceanic, and terrestrial domains. Additionally, we propose potential research directions based on current cutting-edge applications, with the aims of providing critical insights to researchers in the fields of polarization and lidar and inspiring further exciting ideas.

show abstract