Multi-scale gradient domain underwater image enhancement

被引:0
|
作者
Mi, Zetian [1 ]
Liang, Zheng [1 ]
Wang, Yafei [1 ]
Fu, Xianping [1 ]
Chen, Zhengyu [1 ]
机构
[1] Dalian Maritime Univ, Informat Sci & Technol Coll, Dalian 116026, Peoples R China
基金
中国国家自然科学基金;
关键词
Underwater image; Edge-preserving image decomposition; Gradient Domain; Color correction; Contrast enhancement;
D O I
暂无
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
Underwater images often suffer from low visibility, due to the attenuation and scattering of the propagated light, which are caused by the dense and non-uniform medium. Based on the observation that degradation of underwater images occurs both in contrast and color, this paper aims at compensating the contrast and color saturation of the image respectively. To achieve this, we first white balance the degraded image to remove the color casts while producing a natural appearance of the underwater image. Then propose a multi-scale gradient domain contrast enhancement strategy to increase the visibility, and compensate the attenuation of color saturation according to the estimated transmission. Both qualitative and quantitative results demonstrate the effectiveness of the proposed method. Our method yields accurate results with significantly enhanced contrast and superior color, even better than other state-of-the-art methods.
引用
收藏
页数:5
相关论文
共 50 条
  • [1] Single image dehazing via multi-scale gradient domain contrast enhancement
    Mi, Zetian
    Zhou, Huan
    Zheng, Yijun
    Wang, Minghui
    IET IMAGE PROCESSING, 2016, 10 (03) : 206 - 214
  • [2] Multi-scale cascaded attention network for underwater image enhancement
    Zhao, Gaoli
    Wu, Yuheng
    Zhou, Ling
    Zhao, Wenyi
    Zhang, Weidong
    FRONTIERS IN MARINE SCIENCE, 2025, 12
  • [3] Multi-scale Attention Conditional GAN for Underwater Image Enhancement
    Li, Yiming
    Li, Fei
    Li, Zhenbo
    ADVANCES IN COMPUTER GRAPHICS, CGI 2023, PT I, 2024, 14495 : 463 - 475
  • [4] Underwater Image Enhancement with Multi-Scale Residual Attention Network
    Ueki, Yosuke
    Ikehara, Masaaki
    2021 INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), 2021,
  • [5] Underwater image enhancement via extended multi-scale Retinex
    Zhang, Shu
    Wang, Ting
    Dong, Junyu
    Yu, Hui
    NEUROCOMPUTING, 2017, 245 : 1 - 9
  • [6] Multi-scale network with attention mechanism for underwater image enhancement
    Tao, Ye
    Tang, Jinhui
    Zhao, Xinwei
    Zhou, Chen
    Wang, Chong
    Zhao, Zhonglei
    NEUROCOMPUTING, 2024, 595
  • [7] Multi-Scale and Multi-Layer Lattice Transformer for Underwater Image Enhancement
    Hsu, Wei-yen
    Hsu, Yu-yu
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2024, 20 (11)
  • [8] Underwater image enhancement algorithm based on multi-scale block cascade
    Hao Jun-yu
    Yang Hong-bo
    Hou Xia
    Zhang Yang
    CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2023, 38 (09) : 1272 - 1280
  • [9] Transformer-based Multi-scale Underwater Image Enhancement Network
    Yang, Ai-Ping
    Fang, Si-Jie
    Shao, Ming-Fu
    Zhang, Teng-Fei
    Dongbei Daxue Xuebao/Journal of Northeastern University, 2024, 45 (12): : 1696 - 1705
  • [10] Underwater image enhancement based on color balance and multi-scale fusion
    Hu Z.
    Chen Q.
    Zhu D.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2022, 30 (17): : 2133 - 2146