PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement
Light scattering and attenuation in water degrade underwater images with low visibility and color distortion, which often interfere with the high-level visual tasks of underwater autonomous robots. Most existing deep learning methods for underwater image enhancement only supervise the final output o...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/641 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589297765580800 |
|---|---|
| author | Huidi Jia Qiang Wang Bo Fu Zhimin Zheng Yandong Tang |
| author_facet | Huidi Jia Qiang Wang Bo Fu Zhimin Zheng Yandong Tang |
| author_sort | Huidi Jia |
| collection | DOAJ |
| description | Light scattering and attenuation in water degrade underwater images with low visibility and color distortion, which often interfere with the high-level visual tasks of underwater autonomous robots. Most existing deep learning methods for underwater image enhancement only supervise the final output of network and ignore the promotion effect of the intermediate results on the final feature representation. These supervision methods affect the feature representation ability, network efficiency, and ability. In this paper, we present a novel idea of multiple-stage supervision to guide the network to learn useful features correctly and progressively. With this idea, we propose a pixel-wise Progressive Guided Network (PGN) for underwater image enhancement to take advantage of the network’s intermediate results and promote the final enhancement effect. The Pixel-Wise Attention Module is designed by introducing supervision in each stage to progressively promote the representation ability of the features and the recovered image quality. The experimental results on several datasets demonstrate that our method outperforms recent state-of-the-art underwater image enhancement methods. |
| format | Article |
| id | doaj-art-e6fcc599718e432ea8c8ad39e3bcf645 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-e6fcc599718e432ea8c8ad39e3bcf6452025-01-24T13:20:15ZengMDPI AGApplied Sciences2076-34172025-01-0115264110.3390/app15020641PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image EnhancementHuidi Jia0Qiang Wang1Bo Fu2Zhimin Zheng3Yandong Tang4China Mobile Research Institute, Beijing 100055, ChinaKey Laboratory of Manufacturing Industrial Integrated, Shenyang University, Shenyang 110003, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaChina Mobile Research Institute, Beijing 100055, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaLight scattering and attenuation in water degrade underwater images with low visibility and color distortion, which often interfere with the high-level visual tasks of underwater autonomous robots. Most existing deep learning methods for underwater image enhancement only supervise the final output of network and ignore the promotion effect of the intermediate results on the final feature representation. These supervision methods affect the feature representation ability, network efficiency, and ability. In this paper, we present a novel idea of multiple-stage supervision to guide the network to learn useful features correctly and progressively. With this idea, we propose a pixel-wise Progressive Guided Network (PGN) for underwater image enhancement to take advantage of the network’s intermediate results and promote the final enhancement effect. The Pixel-Wise Attention Module is designed by introducing supervision in each stage to progressively promote the representation ability of the features and the recovered image quality. The experimental results on several datasets demonstrate that our method outperforms recent state-of-the-art underwater image enhancement methods.https://www.mdpi.com/2076-3417/15/2/641pixel-wise attentionprogressively guideunderwater image enhancement |
| spellingShingle | Huidi Jia Qiang Wang Bo Fu Zhimin Zheng Yandong Tang PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement Applied Sciences pixel-wise attention progressively guide underwater image enhancement |
| title | PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement |
| title_full | PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement |
| title_fullStr | PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement |
| title_full_unstemmed | PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement |
| title_short | PGN: Progressively Guided Network with Pixel-Wise Attention for Underwater Image Enhancement |
| title_sort | pgn progressively guided network with pixel wise attention for underwater image enhancement |
| topic | pixel-wise attention progressively guide underwater image enhancement |
| url | https://www.mdpi.com/2076-3417/15/2/641 |
| work_keys_str_mv | AT huidijia pgnprogressivelyguidednetworkwithpixelwiseattentionforunderwaterimageenhancement AT qiangwang pgnprogressivelyguidednetworkwithpixelwiseattentionforunderwaterimageenhancement AT bofu pgnprogressivelyguidednetworkwithpixelwiseattentionforunderwaterimageenhancement AT zhiminzheng pgnprogressivelyguidednetworkwithpixelwiseattentionforunderwaterimageenhancement AT yandongtang pgnprogressivelyguidednetworkwithpixelwiseattentionforunderwaterimageenhancement |