2025年 04期

摘要(Abstract)：

针对传统水下图像增强模型缺乏泛化性和灵活性的问题，本文中提出一种多模态退化图文对比(MD-CLIP)模型；通过对比学习训练MD-CLIP模型，MD-CLIP模型将水下低质量图像的图像特征及文本特征编码为多模态退化特征；使用交叉注意力机制和提示嵌入的方式将MD-CLIP模型所预测的多模态退化特征集成到水下图像增强模型中，调整模型的性能和泛化性，并用消融和对比实验验证多模态退化特征的有效性。结果表明：使用交叉注意力机制将MD-CLIP模型预测的多模态退化特征嵌入到水下图像增强模型中，模型的图像增强性能和泛化性能显著提高；MD-CLIP模型可作为一个通用的增强模块添加到其他的图像增强模型中。

关键词(KeyWords)：水下图像增强;多模态退化特征;对比学习;交叉注意力机制

基金项目(Foundation):国家自然科学基金项目(42201465);; 河南省重点研发推广专项项目(232102211015,232102211025)

作者(Author): 熊庆博,陈磊,梁晓莉,刘天须

DOI: 10.13349/j.cnki.jdxbn.20250507.003

参考文献(References)：

[1] WANG H,ZHANG W B,REN P.Self-organized underwater image enhancement[J].ISPRS Journal of Photogrammetry and Remote Sensing,2024,215:1.

[2] ZHOU J C,PANG L,ZHANG D H,et al.Underwater image enhancement method via multi-interval subhistogram perspective equalization[J].IEEE Journal of Oceanic Engineering,2023,48(2):474.

[3] ZHOU J C,SUN J M,ZHANG W S,et al.Multi-view underwater image enhancement method via embedded fusion mechanism[J].Engineering Applications of Artificial Intelligence,2023,121:105946.

[4] PENG L T,ZHU C L,BIAN L H.U-shape transformer for underwater image enhancement[J].IEEE Transactions on Image Processing,2023,32:3066.

[5] LIN S J,LI Z,ZHENG F H,et al.Underwater image enhancement based on adaptive color correction and improved retinex algorithm[J].IEEE Access,2023,11:27620.

[6] WANG H,SUN S X,REN P.Meta underwater camera:a smart protocol for underwater image enhancement[J].ISPRS Journal of Photogrammetry and Remote Sensing,2023,195:462.

[7] WANG Z Y,SHEN L Q,XU M,et al.Domain adaptation for underwater image enhancement[J].IEEE Transactions on Image Processing,2023,32:1442.

[8] HUANG Y F,YUAN F,XIAO F Q,et al.Underwater image enhancement based on zero-reference deep network[J].IEEE Journal of Oceanic Engineering,2023,48(3):903.

[9] SUN B Y,MEI Y P,YAN N,et al.UMGAN:underwater image enhancement network for unpaired image-to-image translation[J].Journal of Marine Science and Engineering,2023,11(2):447.

[10] YANG M,HU J T,LI C Y,et al.An in-depth survey of underwater image enhancement and restoration[J].IEEE Access,2019,7:123638.

[11] IQBAL K,ODETAYO M,JAMES A,et al.Enhancing the low quality images using unsupervised colour correction method[C]//2010 IEEE International Conference on Systems,Man and Cybernetics,October 10-13,2010,Istanbul,Turkey.New York:IEEE,2010:2241-2244.

[12] GHANI A S A,ISA N A M.Underwater image quality enhancement through integrated color model with Rayleigh distribution[J].Journal of Visual Communication and Image Representation,2015,27:219.

[13] GHANI A S A,ISA N A M.Enhancement of low quality underwater image through integrated global and local contrast correction[J].Journal of Visual Communication and Image Representation,2015,37:332.

[14] ANCUTI C O,ANCUTI C,De VLEESCHOUWER C,et al.Color balance and fusion for underwater image enhancement[J].IEEE Transactions on Image Processing,2017,27(1):379.

[15] DREWS P L J,NASCIMENTO E R,BOTELHO S S C,et al.Underwater depth estimation and image restoration based on single images[J].IEEE Computer Graphics and Applications,2016,36(2):24.

[16] HE K M,SUN J,TANG X O.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(12):2341.

[17] LI C Y,GUO J C,GUO C L,et al.A hybrid method for underwater image correction[J].Pattern Recognition Letters,2017,94:62.

[18] AKKAYNAK D,TREIBITZ T.A revised underwater image formation model[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,June 18-23,Salt Lake City,UT,USA.New York:IEEE,2018:5399.

[19] LI J,SKINNER K A,EUSTICE R M,et al.Watergan:unsupervised generative network to enable real-time color correction of monocular underwater images[J].IEEE Robotics and Automation Letters,2017,3(1):387.

[20] JAMADANDI A,MUDENAGUDI U.Exemplar-based underwater image enhancement augmented by wavelet corrected transforms[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,June 16-19,2019,Long Beach,USA.New York:IEEE,2019:11.

[21] UPLAVIKAR P M,WU Z Y,WANG Z Y.All-in-one underwater image enhancement using domain-adversarial learning[EB/OL].(2019-05-30) [2024-03-22].https://doi.org/10.48550/arXiv.1905.13342.

[22] LI C Y,GUO C L,REN W Q,et al.An underwater image enhancement benchmark dataset and beyond[J].IEEE Transactions on Image Processing,2019,29:2629.

[23] LI C Y,ANWAR S,HOU J H,et al.Underwater image enhancement via medium transmission-guided multi-color space embedding[J].IEEE Transactions on Image Processing,2021,30:2098.

[24] HUO F S,LI B H,ZHU X G.Efficient wavelet boost learning-based multi-stage progressive refinement network for underwater image enhancement[C]//2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW),October 11-17,2021,Montreal,BC,Canada.New York:IEEE,2021:1944.

[25] WANG Y D,GUO J C,GAO H,et al.UIEC^2-Net:CNN-based underwater image enhancement using two color space[J].Signal Processing:Image Communication,2021,96:116250.

[26] ZHANG W D,ZHUANG P X,SUN H H,et al.Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement[J].IEEE Transactions on Image Processing,2022,31:1234.

[27] RADFORD A,KIM J W,HALLACY C,et al.Learning transferable visual models from natural language supervision[EB/OL].(2021-02-26) [2024-03-21].https://doi.org/10.48550/arXiv.2103.00020.

[28] LI J N,LI D X,XIONG C M,et al.BLIP:bootstrapping language-image pretraining for unified vision-language understanding and generation[EB/OL].(2022-01-28)[2024- 03-21].https://doi.org/10.48550/arXiv.2201.12086.

[29] WANG R,ZHANG J,DAI D X,et al.Underwater image enhancement via a unified deep learning framework[J].IEEE Transactions on Image Processing,2020,29:1118.

[30] PENG L T,ZHU C L,BIAN L H.U-shape transformer for underwater image enhancement[J].IEEE Transactions on Image Processing,2023,32:4112.

[31] WANG Z D,CUN X D,BAO J M,et al.Uformer:a general U-shaped transformer for image restoration[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),June 18-24,2022,New Orleans,LA,USA.New York:IEEE,2022:17683.

[32] CHEN L Y,CHU X J,ZHANG X Y,et al.Simple baselines for image restoration[C]//AVIDAN S,BROSTOW G,CISSé M,et al.Computer Vision-ECCV 2022:Lecture Notes in Computer Science,Vol 13667.Cham:Springer,2022:17.

[33] WEN J J,CUI J Q,ZHAO Z J,et al.Syreanet:a physically guided underwater image enhancement framework integrating synthetic and real images[C]//2023 IEEE International Conference on Robotics and Automation (ICRA),May 29-June 2,2023.London,United Kingdom.New York:IEEE.2023.DOI:10.1109/ICRA48891.2023.10161531.

[34] ISLAM M J,XIA Y,SATTAR J.Fast underwater image enhancement for improved visual perception[J].IEEE Access,2020,8:124962.

[35] QI Q,LI K Q,ZHENG H Y,et al.Sguie-net:semantic attention guided underwater image enhancement with multi-scale perception[J].IEEE Transactions on Image Processing,2022,31:511.

[36] PENG W Z,ZHOU C H,HU R Z,et al.RAUNE-Net:a residual and attention-driven underwater image enhancement method[C]//ZHAI G T,ZHOU J,YE L,et al.Digital Multimedia Communications:IFTC 2023,Vol 2066.Singapore:Springer,2023:15.