CASF-Net: Underwater Image Enhancement with Color Correction and Spatial Fusion
Abstract
:1. Introduction
- We introduce the network channel adaptive correction module (CACM), which introduces an adaptive factor to solve the problem of insufficient contrast and effectively improve the contrast of underwater images.
- We introduced the spatial multi-scale fusion module (SMFM) to process spatial information of different scales to solve the problem of surface texture distortion and effectively improve underwater image saturation.
- We propose a novel UIE method, CASF-Net, and conduct extensive comparative experiments on the LHUI underwater dataset. The experimental results show that our method outperforms other methods in both qualitative and quantitative aspects.
2. Related Work
2.1. Traditional Enhancement Algorithms
2.2. Deep-Learning-Based Methods
2.3. Underwater Image Datasets
3. Dataset
4. Network Architecture
4.1. Overall Pipline
4.2. CACM
4.3. SMFM
4.4. Loss Function
5. Experiments
5.1. Settings
- Datasets. LHUI contains 12,080 pairs of training images and 1000 pairs of test images, featuring six types of underwater degradation.
- Comparison methods. We compared CASF-Net with 12 UIE methods to verify our performance advantage.
- Evaluation metrics. For the test dataset with reference images, we conducted a full-reference evaluation using the PSNR [47] and SSIM [48] metrics. These two metrics reflect the degree of similarity to the reference, where a higher PSNR [47] value indicates closer image content, and a higher SSIM [48] value reflects a more similar structure and texture.
- Implementation details. We implemented our method using PyTorch and trained it on an NVIDIA Tesla A40 GPU. The network optimization was performed using the ADAM [49] optimizer. The initial learning rate was set to . The total number of iterations was 2 K. The batch size was 128, and the block size of the input image was 128 × 128.
- Algorithm introduction. We briefly introduce the contrast methods used, as shown in Table 1.
5.2. Comparisons with State-of-the-Art Methods
Methods | Reference | Introduction |
---|---|---|
LiteEnhanceNet | [50] | Lightweight CNN Network Model Based on Depthwise Separable Convolution |
LANet | [26] | Image Enhancement Algorithm Using Multi-Scale Spatial Information and Parallel Attention Mechanism |
CLUIE | [18] | Underwater image enhancement algorithms with multiple reference learning |
GC | [19] | Based on the basic knowledge of human vision |
MSCNN | [16] | Image Dehazing Method Based on Multi-Scale Deep Neural Networks |
DCP | [10] | Image dehazing method using the dark channel prior |
FspiralGAN | [15] | Adopting a GAN network model with an equal-channel design |
CLAHE | [27] | Adaptive Histogram Equalization Enhancement Method |
MetaUE | [33] | Model-based Underwater Image Enhancement Algorithm |
GDCP | [20] | Universal Image Restoration Algorithm Using the Dark Channel Prior |
UDCP | [9] | A method for estimating transmission in underwater environments has been proposed, along with a corresponding underwater image enhancement algorithm |
PUIE | [17] | Underwater Image Enhancement Method Based on Probabilistic Networks |
Methods | PSNR (dB) ↑ | SSIM ↑ | MSE |
---|---|---|---|
LiteEnhanceNet [50] | 24.86 | 0.9175 | 0.8128 |
LANet [26] | 21.36 | 0.9142 | 1.1893 |
CLUIE [18] | 18.92 | 0.8877 | 1.8170 |
GC [19] | 15.65 | 0.8421 | 3.8121 |
MSCNN [16] | 13.41 | 0.7568 | 5.6020 |
DCP [10] | 12.67 | 0.7849 | 6.3114 |
FspiralGAN [15] | 21.14 | 0.8507 | 1.8449 |
CLAHE [27] | 19.43 | 0.9086 | 1.5046 |
MetaUE [33] | 15.69 | 0.7937 | 3.0617 |
GDCP [20] | 13.76 | 0.8209 | 5.2951 |
UDCP [9] | 10.55 | 0.5591 | 10.1081 |
PUIE [17] | 23.39 | 0.9302 | 0.7860 |
Ours | 26.41 | 0.9401 | 0.6881 |
5.3. Ablation Studies
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Urabe, T.; Ura, T.; Tsujimoto, T.; Hotta, H. Next-generation technology for ocean resources exploration (Zipangu-in-the-Ocean) project in Japan. In Proceedings of the OCEANS 2015-Genova, Genova, Italy, 18–21 May 2015; pp. 1–5. [Google Scholar]
- Lurton, X. An Introduction to Underwater Acoustics: Principles and Applications; Springer Science & Business Media: Berlin, Germany, 2002. [Google Scholar]
- Raveendran, S.; Patil, M.D.; Birajdar, G.K. Underwater image enhancement: A comprehensive review, recent trends, challenges and applications. Artif. Intell. Rev. 2021, 54, 5413–5467. [Google Scholar] [CrossRef]
- Wozniak, B.; Dera, J. Light Absorption by Suspended Particulate Matter (SPM) in Sea Water; Springer: Berlin/Heidelberg, Germany, 2007. [Google Scholar]
- Stramski, D.; Boss, E.; Bogucki, D.; Voss, K.J. The role of seawater constituents in light backscattering in the ocean. Prog. Oceanogr. 2004, 61, 27–56. [Google Scholar] [CrossRef]
- Ancuti, C.; Ancuti, C.O.; Haber, T.; Bekaert, P. Enhancing underwater images and videos by fusion. In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 16–21 June 2012; pp. 81–88. [Google Scholar]
- Land, E.H.; McCann, J.J. Lightness and retinex theory. J. Opt. Soc. Am. 1971, 61, 1–11. [Google Scholar] [CrossRef] [PubMed]
- Fu, X.; Zhuang, P.; Huang, Y.; Liao, Y.; Zhang, X.-P.; Ding, X. A retinex-based enhancing approach for single underwater image. In Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP), Paris, France, 27–30 October 2014; pp. 4572–4576. [Google Scholar]
- Drews, P.; Nascimento, E.; Moraes, F.; Botelho, S.; Campos, M. Transmission estimation in underwater single images. In Proceedings of the IEEE international conference on computer vision workshops, Sydney, Australia, 2–8 December 2013; pp. 825–830. [Google Scholar]
- He, K.; Sun, J.; Tang, X. Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 2010, 33, 2341–2353. [Google Scholar]
- Wang, Y.; Liu, H.; Chau, L.-P. Single underwater image restoration using adaptive attenuation-curve prior. IEEE Trans. Circuits Syst. Regul. Pap. 2017, 65, 992–1002. [Google Scholar] [CrossRef]
- Li, J.; Skinner, K.A.; Eustice, R.M.; Johnson-Roberson, M. WaterGAN: Unsupervised generative network to enable real-time color correction of monocular underwater images. IEEE Robot. Autom. Lett. 2017, 3, 387–394. [Google Scholar] [CrossRef]
- Fabbri, C.; Islam, M.J.; Sattar, J. Enhancing underwater imagery using generative adversarial networks. In Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, 21–25 May 2018; pp. 7159–7165. [Google Scholar]
- Li, C.; Guo, J.; Guo, C. Emerging from water: Underwater image color correction based on weakly supervised color transfer. IEEE Signal Process. Lett. 2018, 25, 323–327. [Google Scholar] [CrossRef]
- Han, R.; Guan, Y.; Yu, Z.; Liu, P.; Zheng, H. Underwater image enhancement based on a spiral generative adversarial framework. IEEE Access 2020, 8, 218838–218852. [Google Scholar] [CrossRef]
- Ren, W.; Liu, S.; Zhang, H.; Pan, J.; Cao, X.; Yang, M.-H. Single image dehazing via multi-scale convolutional neural networks. In Proceedings of the Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016; Proceedings, Part II 14. pp. 154–169. [Google Scholar]
- Fu, Z.; Wang, W.; Huang, Y.; Ding, X.; Ma, K.-K. Uncertainty inspired underwater image enhancement. In Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel, 23–27 October 2022; pp. 465–482. [Google Scholar]
- Li, K.; Wu, L.; Qi, Q.; Liu, W.; Gao, X.; Zhou, L.; Song, D. Beyond single reference for training: Underwater image enhancement via comparative learning. IEEE Trans. Circuits Syst. Video Technol. 2022, 33, 2561–2576. [Google Scholar] [CrossRef]
- Schlick, C. Quantization techniques for visualization of high dynamic range pictures. In Photorealistic Rendering Techniques; Springer: Berlin/Heidelberg, Germany, 1995; pp. 7–20. [Google Scholar]
- Peng, Y.-T.; Cao, K.; Cosman, P.C. Generalization of the dark channel prior for single image restoration. IEEE Trans. Image Process. 2018, 27, 2856–2868. [Google Scholar] [CrossRef]
- Wang, Y.; Song, W.; Fortino, G.; Qi, L.-Z.; Zhang, W.; Liotta, A. An experimental-based review of image enhancement and image restoration methods for underwater imaging. IEEE Access 2019, 7, 140233–140251. [Google Scholar] [CrossRef]
- Islam, M.J.; Xia, Y.; Sattar, J. Fast underwater image enhancement for improved visual perception. IEEE Robot. Autom. Lett. 2020, 5, 3227–3234. [Google Scholar] [CrossRef]
- Li, C.; Guo, C.; Ren, W.; Cong, R.; Hou, J.; Kwong, S.; Tao, D. An underwater image enhancement benchmark dataset and beyond. IEEE Trans. Image Process. 2019, 29, 4376–4389. [Google Scholar] [CrossRef]
- Peng, L.; Zhu, C.; Bian, L. U-shape transformer for underwater image enhancement. IEEE Trans. Image Process. 2023, 32, 3066–3079. [Google Scholar] [CrossRef]
- Xie, Y.; Kong, L.; Chen, K.; Zheng, Z.; Yu, X.; Yu, Z.; Zheng, B. UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 16–22 June 2024; pp. 22358–22367. [Google Scholar]
- Liu, S.; Fan, H.; Lin, S.; Wang, Q.; Ding, N.; Tang, Y. Adaptive learning attention network for underwater image enhancement. IEEE Robot. Autom. Lett. 2022, 7, 5326–5333. [Google Scholar] [CrossRef]
- Zuiderveld, K. Contrast limited adaptive histogram equalization. In Graphics Gems IV; Elsevier: Amsterdam, The Netherlands, 1994; pp. 474–485. [Google Scholar]
- Jiang, J.; Ye, T.; Bai, J.; Chen, S.; Chai, W.; Jun, S.; Liu, Y.; Chen, E. Five A + Network: You Only Need 9K Parameters for Underwater Image Enhancement. arXiv 2023, arXiv:2305.08824. [Google Scholar]
- Fu, Z.; Lin, H.; Yang, Y.; Chai, S.; Sun, L.; Huang, Y.; Ding, X. Unsupervised underwater image restoration: From a homology perspective. In Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada, 28 February–1 March 2022; pp. 643–651. [Google Scholar]
- Zhang, W.; Zhuang, P.; Sun, H.-H.; Li, G.; Kwong, S.; Li, C. Underwater image enhancement via minimal color loss and locally adaptive contrast enhancement. IEEE Trans. Image Process. 2022, 31, 3997–4010. [Google Scholar] [CrossRef]
- Galdran, A.; Pardo, D.; Picón, A.; Alvarez-Gila, A. Automatic red-channel underwater image restoration. J. Vis. Commun. Image Represent. 2015, 26, 132–145. [Google Scholar] [CrossRef]
- Zhang, W.; Zhou, L.; Zhuang, P.; Li, G.; Pan, X.; Zhao, W.; Li, C. Underwater image enhancement via weighted wavelet visual perception fusion. IEEE Trans. Circuits Syst. Video Technol. 2023, 34, 2469–2483. [Google Scholar] [CrossRef]
- Zhang, Z.; Yan, H.; Tang, K.; Duan, Y. MetaUE: Model-based meta-learning for underwater image enhancement. arXiv 2023, arXiv:2303.06543. [Google Scholar]
- Guo, C.; Wu, R.; Jin, X.; Han, L.; Zhang, W.; Chai, Z.; Li, C. Underwater ranker: Learn which is better and how to be better. In Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA, 7–14 February 2023; pp. 702–709. [Google Scholar]
- Chen, C.; Chen, Q.; Xu, J.; Koltun, V. Learning to See in the Dark. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 8–22 June 2018; pp. 3291–3300. [Google Scholar]
- Series, B. Methodology for the subjective assessment of the quality of television pictures. Recomm. ITU-R BT 2012, 13, 500. [Google Scholar]
- Bai, S.; Koltun, V.; Kolter, J.Z. Multiscale deep equilibrium models. Adv. Neural Inf. Process. Syst. 2020, 33, 5238–5250. [Google Scholar]
- Gao, S.-H.; Cheng, M.-M.; Zhao, K.; Zhang, X.-Y.; Yang, M.-H.; Torr, P. Res2net: A new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 43, 652–662. [Google Scholar] [CrossRef]
- Ren, S.; Zhou, D.; He, S.; Feng, J.; Wang, X. Shunted self-attention via multi-scale token aggregation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 10853–10862. [Google Scholar]
- Wu, Y.-H.; Liu, Y.; Zhan, X.; Cheng, M.-M. P2T: Pyramid pooling transformer for scene understanding. IEEE Trans. Pattern Anal. Mach. Intell. 2022, 45, 12760–12771. [Google Scholar] [CrossRef]
- Chen, Y.; Fan, H.; Xu, B.; Yan, Z.; Kalantidis, Y.; Rohrbach, M.; Yan, S.; Feng, J. Drop an octave: Reducing spatial redundancy in convolutional neural networks with octave convolution. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 3435–3444. [Google Scholar]
- Pan, Z.; Cai, J.; Zhuang, B. Fast vision transformers with hilo attention. Adv. Neural Inf. Process. Syst. 2022, 35, 14541–14554. [Google Scholar]
- Si, C.; Yu, W.; Zhou, P.; Zhou, Y.; Wang, X.; Yan, S. Inception transformer. Adv. Neural Inf. Process. Syst. 2022, 35, 23495–23509. [Google Scholar]
- Cui, Y.; Ren, W.; Cao, X.; Knoll, A. Focal network for image restoration. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France, 2–6 October 2023; pp. 13001–13011. [Google Scholar]
- Cho, S.-J.; Ji, S.-W.; Hong, J.-P.; Jung, S.-W.; Ko, S.-J. Rethinking coarse-to-fine approach in single image deblurring. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada, 10–17 October 2021; pp. 4641–4650. [Google Scholar]
- Cui, Y.; Tao, Y.; Bing, Z.; Ren, W.; Gao, X.; Cao, X.; Huang, K.; Knoll, A. Selective frequency network for image restoration. In Proceedings of the The Eleventh International Conference on Learning Representations, Kigali, Rwanda, 1–5 May 2023. [Google Scholar]
- Korhonen, J.; You, J. Peak signal-to-noise ratio revisited: Is simple beautiful? In Proceedings of the 2012 Fourth International Workshop on Quality of Multimedia Experience, Melbourne, Australia, 5–7 July 2012; pp. 37–38. [Google Scholar]
- Hore, A.; Ziou, D. Image quality metrics: PSNR vs. SSIM. In Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey, 23–26 August 2010; pp. 2366–2369. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Zhang, S.; Zhao, S.; An, D.; Li, D.; Zhao, R. LiteEnhanceNet: A lightweight network for real-time single underwater image enhancement. Expert Syst. Appl. 2024, 240, 122546. [Google Scholar] [CrossRef]
(a) | (b) | (c) | |
---|---|---|---|
baseline | ✓ | ✓ | ✓ |
CACM | ✓ | ✓ | |
SMFM | ✓ | ||
PSNR (dB) ↑ | 23.84 | 26.17 | 26.41 |
SSIM ↑ | 0.9226 | 0.9325 | 0.9401 |
MSE | 0.9525 | 0.7132 | 0.6881 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chen, K.; Li, Z.; Zhou, F.; Yu, Z. CASF-Net: Underwater Image Enhancement with Color Correction and Spatial Fusion. Sensors 2025, 25, 2574. https://doi.org/10.3390/s25082574
Chen K, Li Z, Zhou F, Yu Z. CASF-Net: Underwater Image Enhancement with Color Correction and Spatial Fusion. Sensors. 2025; 25(8):2574. https://doi.org/10.3390/s25082574
Chicago/Turabian StyleChen, Kai, Zhenhao Li, Fanting Zhou, and Zhibin Yu. 2025. "CASF-Net: Underwater Image Enhancement with Color Correction and Spatial Fusion" Sensors 25, no. 8: 2574. https://doi.org/10.3390/s25082574
APA StyleChen, K., Li, Z., Zhou, F., & Yu, Z. (2025). CASF-Net: Underwater Image Enhancement with Color Correction and Spatial Fusion. Sensors, 25(8), 2574. https://doi.org/10.3390/s25082574