WS-UIENet: a wavelet-decoupled semantics-guided underwater image enhancement network

Abstract

Underwater images often suffer from severe degradation caused by wavelength-dependent light absorption and scattering, resulting in color distortion, illumination attenuation, low contrast, and loss of fine structural details. Existing underwater image enhancement (UIE) approaches have achieved promising progress, yet they still face notable limitations. Prior-based methods usually depend on restrictive physical assumptions and therefore show limited adaptability to diverse underwater environments, whereas learning-based methods often rely on increasingly complex network architectures, leading to high computational cost and limited practicality in resource-constrained underwater platforms. To overcome these challenges, we propose a wavelet-decoupled semantic-guided underwater image enhancement network (WS-UIENet), which integrates the wavelet transform with textual semantic guidance. Specifically, WS-UIENet adopts a two-stage enhancement framework, which comprises a wavelet-based frequency enhancement stage and a semantic-guided spatial refinement stage. In the frequency enhancement stage, wavelet decomposition is used to separate low-frequency illumination and color degradation from high-frequency texture and structural degradation, enabling targeted restoration of different degradation components while reducing the learning burden of the network. In the spatial refinement stage, textual semantic features extracted using a vision–language model are injected into the bottleneck layer as conditional modulation signals, providing perceptually meaningful guidance for semantic-consistent enhancement. To our knowledge, this work is the first to jointly exploit wavelet-based frequency decomposition and textual semantic guidance within a unified framework for efficient UIE. Comprehensive experiments on four real-world underwater datasets demonstrate that the proposed WS-UIENet achieves competitive performance compared with 20 state-of-the-art UIE methods. In addition, WS-UIENet achieves comparable performance to the strongest text-guided UIE method while nearly halving computational complexity, demonstrating a favorable balance between effectiveness and efficiency. Code and models are available at https://github.com/INDTLab/WS-UIENet.

Keywords

Underwater image enhancement / Wavelet transform / Image–text fusion / Deep learning

References

[1] An SM, Xu LH, Deng ZC, Zhang HP (2024) HFM: a hybrid fusion method for underwater image enhancement. Eng Appl Artif Intell 127:107219. https://doi.org/10.1016/j.engappai.2023.107219

[2] Ancuti C, Ancuti CO, Haber T, Bekaert P (2012) Enhancing underwater images and videos by fusion. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 81–88. https://doi.org/10.1109/CVPR.2012.6247661

[3] Ancuti CO, Ancuti C, De Vleeschouwer C, Bekaert P (2018) Color balance and fusion for underwater image enhancement. IEEE Trans Image Process 27(1):379–393. https://doi.org/10.1109/TIP.2017.2759252

[4] Bai JS, Yin YH, He QY, Li YX, Zhang XF (2025) RetinexMamba: Retinex-based Mamba for low-light image enhancement. In: International Conference on Neural Information Processing. Springer, pp 427–442. https://doi.org/10.1007/978-981-96-6596-9_30

[5] Berman D, Levy D, Avidan S, Treibitz T (2020) Underwater single image color restoration using haze-lines and a new quantitative dataset. IEEE Trans Pattern Anal Mach Intell 43(8):2822–2837. https://doi.org/10.1109/TPAMI.2020.2977624

[6] Berman D, Treibitz T, Avidan S (2017) Diving into haze-lines: color restoration of underwater images. In: British Machine Vision Conference (BMVC). BMVA Press, pp 1–12

[7] Cai YH, Bian H, Lin J, Wang HQ, Timofte R, Zhang YL (2023) Retinexformer: one-stage retinex-based transformer for low-light image enhancement. In: 2023 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 12470–12479. https://doi.org/10.1109/ICCV51070.2023.01149

[8] Chen WW, Lei YT, Luo SH, Zhou ZY, Li MX, Pun CM (2024) UWFormer: underwater image enhancement via a semi-supervised multi-scale transformer. In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1–8. https://doi.org/10.1109/IJCNN60899.2024.10651366

[9] Drews Jr P, do Nascimento E, Moraes F, Botelho S, Campos M (2013) Transmission estimation in underwater single images. In: Proceedings of the IEEE International Conference on Computer Vision Workshops. IEEE, pp 825–830. https://doi.org/10.1109/ICCVW.2013.113

[10] Fu ZQ, Wang W, Huang Y, Ding XH, Ma KK (2022) Uncertainty inspired underwater image enhancement. In: 17th European Conference on Computer Vision (ECCV). Springer, pp 465–482. https://doi.org/10.1007/978-3-031-19797-0_27

[11] Gaintseva T, Benning M, Slabaugh G (2024) RAVE: residual vector embedding for CLIP-guided backlit image enhancement. In: 18th European Conference on Computer Vision (ECCV). Springer, pp 412–428. https://doi.org/10.1007/978-3-031-72986-7_24

[12] Guo CL, Wu RQ, Jin X, Han LH, Zhang WD, Chai Z et al (2023) Underwater ranker: learn which is better and how to be better. In: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI, pp 702–709

[13] He KM, Sun J, Tang XO (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341–2353. https://doi.org/10.1109/TPAMI.2010.168

[14] Huang DM, Wang Y, Song W, Sequeira J, Mavromatis S (2018) Shallow-water image enhancement using relative global histogram stretching based on adaptive parameter acquisition. In: MultiMedia Modeling: 24th International Conference (MMM). Springer, pp 453–465. https://doi.org/10.1007/978-3-319-73603-7_37

[15] Ke JJ, Wang QF, Wang YL, Milanfar P, Yang F (2021) MUSIQ: multi-scale image quality transformer. In: 18th IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 5128–5137.https://doi.org/10.1109/ICCV48922.2021.00510

[16] Khan A, Ali S, Malik AS, Anwer A, Meriaudeau F (2016) Underwater image enhancement by wavelet based fusion. In: 2016 IEEE International Conference on Underwater System Technology: Theory and Applications (USYS). IEEE, pp 83–88. https://doi.org/10.1109/USYS.2016.7893927

[17] Land EH. The retinex theory of color vision. Sci Am, 1977, 237(6): 108

[18] Li CY, Anwar S, Hou JH, Cong RM, Guo CL, Ren WQ (2021) Underwater image enhancement via medium transmission-guided multi-color space embedding. IEEE Trans Image Process 30:4985–5000. https://doi.org/10.1109/TIP.2021.3076367

[19] Li CY, Guo CL, Ren WQ, Cong RM, Hou JH, Kwong S et al (2020) An underwater image enhancement benchmark dataset and beyond. IEEE Trans Image Process 29:4376–4389. https://doi.org/10.1109/TIP.2019.2955241

[20] Liang ZX, Li CY, Zhou SC, Feng RC, Loy CC (2023) Iterative prompt learning for unsupervised backlit image enhancement. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. IEEE, pp 8060–8069. https://doi.org/10.1109/ICCV51070.2023.00743

[21] Lin BS, Dong JY, Dong XH (2025) Perception-aware underwater image quality assessment: dataset, perceptual quality scores and assessment network. IEEE Trans Circuits Syst Video Technol 35(11):11113–11128. https://doi.org/10.1109/TCSVT.2025.3574860

[22] Liu SB, Fan HJ, Wang Q, Han Z, Guan Y, Tang YD (2024a) Wavelet-pixel domain progressive fusion network for underwater image enhancement. Knowledge-Based Syst 299:112049. https://doi.org/10.1016/j.knosys.2024.112049

[23] Liu SX, Li KQ, Ding YL, Qi Q (2024b) Underwater image enhancement by diffusion model with customized clip-classifier. Preprint at arXiv:2405.16214

[24] Ma ZY, Oh C (2022) A wavelet-based dual-stream network for underwater image enhancement. In: 47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 2769–2773. https://doi.org/10.1109/ICASSP43922.2022.9747781

[25] Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell, 1989, 11(7): 674-693

[26] Panetta K, Gao C, Agaian S (2016) Human-visual-system-inspired underwater image quality measures. IEEE J Ocean Eng 41(3):541–551. https://doi.org/10.1109/JOE.2015.2469915

[27] Peng LT, Zhu CL, Bian LH (2023) U-shape transformer for underwater image enhancement. IEEE Trans Image Process 32:3066–3079. https://doi.org/10.1109/TIP.2023.3276332

[28] Peng YT, Cao KM, Cosman PC (2018) Generalization of the dark channel prior for single image restoration. IEEE Trans Image Process 27(6):2856–2868. https://doi.org/10.1109/TIP.2018.2813092

[29] Qi H, Zhou HY, Dong JY, Dong XH (2024) Deep color-corrected multi-scale retinex network for underwater image enhancement. IEEE Trans Geosci Remote Sens 62:1–13. https://doi.org/10.1109/TGRS.2023.3338611

[30] Qi Q, Li KQ, Zheng HY, Gao X, Hou GJ, Sun K (2022) SGUIE-Net: semantic attention guided underwater image enhancement with multi-scale perception. IEEE Trans Image Process 31:6816–6830. https://doi.org/10.1109/TIP.2022.3216208

[31] Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S et al (2021) Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML). PMLR, pp 8748–8763. https://proceedings.mlr.press/v139/radford21a.html

[32] Wang H, Frery AC, Li MJ, Ren P (2023) Underwater image enhancement via histogram similarity-oriented color compensation complemented by multiple attribute adjustment. Intell Mar Technol Syst 1:12. https://doi.org/10.1007/s44295-023-00015-y

[33] Wang RY, Li WH, Liu XH, Li CY, Zhang ZC, Min XK et al (2025a) HazeCLIP: towards language guided real-world image dehazing. In: 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 1–5. https://doi.org/10.1109/ICASSP49660.2025.10889509

[34] Wang X, Luo ZH, Huang W, Zhang YZ, Hu RQ (2025b) Optimized UNet framework with a joint loss function for underwater image enhancement. Sci Rep 15(1):7327. https://doi.org/10.1038/s41598-025-91839-7

[35] Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612. https://doi.org/10.1109/TIP.2003.819861

[36] Xu SX, Qi H, Wang W, Huang C, Wen J, Dong JY (2025) A semi-supervised physics-aware triple-stream underwater image enhancement network. Preprint at arXiv:2307.11470v7 

[37] Xu SX, Liu YB, Huang C, Dong JY, Dong XH (2026) Retinex meets language: a physics-semantics-guided underwater image enhancement network. Preprint at arXiv:2603.07076

[38] Yang M, Sowmya A. An underwater color image quality evaluation metric. IEEE Trans Image Process, 2015, 24(12): 6062-6071

[39] Zhang H, Zhang WQ, Yuan H, Bai SZ, Tian YB, Liu ZH (2025a) Image enhancement in turbid water using multiscale weighted features and attention mechanisms. Intell Mar Technol Syst 3:35. https://doi.org/10.1007/s44295-025-00086-z

[40] Zhang HP, Xu HL, Yu XS, Zhang XY, Gao XJ, Wu CD (2025b) CDF-UIE: leveraging cross-domain fusion for underwater image enhancement. IEEE Trans Geosci Remote Sens 63:4203715. https://doi.org/10.1109/TGRS.2025.3553557

[41] Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 586–595. https://doi.org/10.1109/CVPR.2018.00068

[42] Zhang S, Wang T, Dong JY, Yu H (2017) Underwater image enhancement via extended multi-scale retinex. Neurocomputing 245:1–9. https://doi.org/10.1016/j.neucom.2017.03.029

[43] Zhang WD, Liu QM, Lu HM, Wang JP, Liang J (2025c) Underwater image enhancement via wavelet decomposition fusion of advantage contrast. IEEE Trans Circuits Syst Video Technol 35(8):7807–7820. https://doi.org/10.1109/TCSVT.2025.3545595

[44] Zhang WD, Wang MZ, Zhuang PX, Liu DH (2026) Underwater image enhancement via advantage feature weighted fusion. IEEE Trans Circuits Syst Video Technol 36(2):2006–2018. https://doi.org/10.1109/TCSVT.2025.3603059

[45] Zhang WD, Zhou L, Zhuang PX, Li GH, Pan XP, Zhao WY et al (2024) Underwater image enhancement via weighted wavelet visual perception fusion. IEEE Trans Circuits Syst Video Technol 34(4):2469–2483. https://doi.org/10.1109/TCSVT.2023.3299314

[46] Zhang WD, Zhuang PX, Sun HH, Li GH, Kwong S, Li CY (2022) Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement. IEEE Trans Image Process 31:3997–4010. https://doi.org/10.1109/TIP.2022.3177129

[47] Zhuang PX, Wu JM, Porikli F, Li CY (2022) Underwater image enhancement with hyper-laplacian reflectance priors. IEEE Trans Image Process 31:5442–5455. https://doi.org/10.1109/TIP.2022.3196546

[48] Zuiderveld K (1994) Contrast limited adaptive histogram equalization. In: Graphics gems IV. Academic Press Professional Inc., San Diego, pp 474–485. https://dl.acm.org/doi/10.5555/180895.180940

Funding

National Natural Science Foundation of China(No. 42576200)

Key Technology Research and Development Program of Shandong Province(No. 2024ZLGX06)

RIGHTS & PERMISSIONS

The Author(s)