Hierarchical decomposition-based underwater image enhancement network with auxiliary gradient guidance

被引:0
|
作者
Xie, Jing [1 ]
Deng, Xing [1 ]
Shao, Haijian [1 ,2 ]
Jiang, Yingtao [2 ]
机构
[1] Jiangsu University of Science and Technology, School of Computer, Jiangsu, Zhenjiang, China
[2] University of Nevada, Department of Electrical and Computer Engineering, Las Vegas,NV, United States
关键词
Underwater image enhancement is challenging due to the complex and variable degradations induced by environmental disturbances. While deep learning methods recently have achieved substantial progress in image enhancement; their performance is still hampered by the limited understanding of underwater image characteristics. To address this; we propose the hierarchical decomposition-based underwater image enhancement network (HDNet); which tackles key elements of underwater image degradation. Our model employs macroscopic channel decomposition and microscopic pixel decomposition to correct color distortion from light attenuation and restore detail loss from scattering. In the pixel decomposition process; HDNet interprets pixels as perturbed light signals and refines image details by representing and modulating these signals; emulating the principles of the Fourier transform. In addition; we introduce an auxiliary gradient guidance strategy to mitigate the effects of poor reference images during training. HDNet demonstrates good performance across multiple datasets. Notably; on the underwater image enhancement dataset; a real-world underwater dataset; HDNet achieves a peak signal-to-noise ratio of 24.158 dB and a structural similarity index of 0.923; outperforming many previous state-of-the-art models. Its low parameter count and computational efficiency make it suitable for practical; real-world applications. © 2024 SPIE and IS&T;
D O I
10.1117/1.JEI.33.5.053028
中图分类号
学科分类号
摘要
引用
收藏
相关论文
共 50 条
  • [41] Severely Degraded Underwater Image Enhancement with a Wavelet-based Network
    Takao, Shunsuke
    Kita, Tsukasa
    Hirabayashi, Taketsugu
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2022, 13 (08) : 7 - 13
  • [42] Underwater image enhancement based on multiscale fusion generative adversarial network
    Dai, Yating
    Wang, Jianyu
    Wang, Hao
    He, Xin
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024, 15 (04) : 1331 - 1341
  • [43] Underwater Image Enhancement Based on Hybrid Enhanced Generative Adversarial Network
    Xu, Danmi
    Zhou, Jiajia
    Liu, Yang
    Min, Xuyu
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2023, 11 (09)
  • [44] Underwater Image Enhancement Method Based on Feature Fusion Neural Network
    Tian, Yuan
    Xu, Yuang
    Zhou, Jun
    IEEE ACCESS, 2022, 10 : 107536 - 107548
  • [45] Underwater Image Enhancement Based on Zero-Reference Deep Network
    Huang, Yifan
    Yuan, Fei
    Xiao, Fengqi
    Lu, Jianxiang
    Cheng, En
    IEEE JOURNAL OF OCEANIC ENGINEERING, 2023, 48 (03) : 903 - 924
  • [46] Underwater Image Enhancement With Lightweight Cascaded Network
    Jiang, Nanfeng
    Chen, Weiling
    Lin, Yuting
    Zhao, Tiesong
    Lin, Chia-Wen
    IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 : 4301 - 4313
  • [47] A Decomposition-based Approach of Global Norms for Hierarchical Normative Systems
    Missaoui, Ezzine
    Mazigh, Belhassen
    Bhiri, Sami
    Hilaire, Vincent
    KNOWLEDGE-BASED AND INTELLIGENT INFORMATION & ENGINEERING SYSTEMS (KES-2018), 2018, 126 : 778 - 787
  • [48] Guidance Network with Staged Learning for Image enhancement
    Liang, Luming
    Zharkov, Ilya
    Amjadi, Faezeh
    Joze, Hamid Reza Vaezi
    Pradeep, Vivek
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 836 - 845
  • [49] Special Agents Policy Gradient In Value Decomposition-based Approach
    Kang, Qitong
    Wang, Fuyong
    Liu, Zhongxin
    Chen, Zengqiang
    2023 IEEE 12TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE, DDCLS, 2023, : 1387 - 1391
  • [50] Underwater image restoration based on progressive guidance
    Zhang, Jianghe
    Chen, Weiling
    Lin, Zuxin
    Wei, Hongan
    Zhao, Tiesong
    SIGNAL PROCESSING, 2024, 223