在水下環境中如何捕捉清晰的影像是海洋工程中的一個重要問題。 獲取清晰的水下影像面臨許多挑戰。 例如，氣候、環境和人為因素等。其中最主要的原因是色散造成的霧化效應，以及光在水中傳播時各波長的能量衰減不一致造成的色偏。 Li 等學者關注水下影像的色偏和影像低對比度問題，並通過一種具有多色空間嵌入編碼器和介質透射引導網路的水下影像增強網路架構。儘管視覺品質和量化指標都優於最先進的方法，但色域空間和影像的動態範圍似乎具有更大改善空間，改善其可見細節。因此，本研究提出了用於使用深度學習模型的推斷退化模型來進一步改善影像動態範圍。解決了水下影像中動態範圍和亮度有限的問題。定量和定性結果表明，與其他最近的方法相比，本研究的網路在水下影像增強基準 (UIEB) 數據集中表現相對較好，未來有望應用於不同類型的水下工作和環境，減少水下影像時常出現的嚴重退化問題。

Capturing clear images in underwater environments is a critical challenge in marine engineering. Obtaining clear underwater images faces many obstacles, such as climate, environmental, and human factors. The primary cause is the fogging effect caused by dispersion and the color distortion resulting from the uneven attenuation of energy at different wavelengths as light propagates through water. Li et al. address the color distortion and low contrast issues in underwater images and propose an underwater image enhancement network architecture with a multi-color space embedding and medium transmission guidance network. While the visual quality and quantitative metrics are superior to state-of-the-art methods, the color space and images seem to have a larger dynamic range and visible details that can be improved. Therefore, we propose using a deep learning model to infer the degradation model to further improve the image's dynamic range in underwater environments. We address the limited dynamic range and brightness issues in underwater images. Quantitative and qualitative results show that our network performs relatively well in the Underwater Image Enhancement Benchmark (UIEB) dataset compared to other recent methods. It is expected to be applied to different types of underwater work and environments, reducing the severe degradation issues commonly encountered in underwater images.

[1] C. Li, S. Anwar, J. Hou, R. Cong, C. Guo and W. Ren, "Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding," in IEEE Transactions on Image Processing, vol. 30, pp. 4985-5000, 2021, doi: 10.1109/TIP.2021.3076367.
[2] M. Han, Z. Lyu, T. Qiu and M. Xu, "A Review on Intelligence Dehazing and Color Restoration for Underwater Images," in IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 50, no. 5, pp. 1820-1832, May 2020, doi: 10.1109/TSMC.2017.2788902.
[3] P. L. J. Drews, E. R. Nascimento, S. S. C. Botelho and M. F. Montenegro Campos, "Underwater Depth Estimation and Image Restoration Based on Single Images," in IEEE Computer Graphics and Applications, vol. 36, no. 2, pp. 24-35, Mar.-Apr. 2016, doi: 10.1109/MCG.2016.26.
[4] K. He, J. Sun and X. Tang, "Single Image Haze Removal Using Dark Channel Prior," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341-2353, Dec. 2011, doi: 10.1109/TPAMI.2010.168.
[5] C. -Y. Li, J. -C. Guo, R. -M. Cong, Y. -W. Pang and B. Wang, "Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior," in IEEE Transactions on Image Processing, vol. 25, no. 12, pp. 5664-5677, Dec. 2016, doi: 10.1109/TIP.2016.2612882.
[6] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998, doi: 10.1109/5.726791.
[7] C. Li et al., "ASIF-Net: Attention Steered Interweave Fusion Network for RGB-D Salient Object Detection," in IEEE Transactions on Cybernetics, vol. 51, no. 1, pp. 88-100, Jan. 2021, doi: 10.1109/TCYB.2020.2969255.
[8] G. Huang, Z. Liu, G. Pleiss, L. v. d. Maaten and K. Q. Weinberger, "Convolutional Networks with Dense Connectivity," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 12, pp. 8704-8716, 1 Dec. 2022, doi: 10.1109/TPAMI.2019.2918284.
[9] C. Li, J. Guo and C. Guo, "Emerging From Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer," in IEEE Signal Processing Letters, vol. 25, no. 3, pp. 323-327, March 2018, doi: 10.1109/LSP.2018.2792050.
[10] C. Li, S. Anwar, and F. Porikli, “Underwater scene prior inspired deep underwater image and video enhancement,” in Pattern Recognit, vol. 98, pp. 107038–107049, Feb. 2020.
[11] C. Li et al., "An Underwater Image Enhancement Benchmark Dataset and Beyond," in IEEE Transactions on Image Processing, vol. 29, pp. 4376-4389, 2020, doi: 10.1109/TIP.2019.2955241.
[12] B. Cai, X. Xu, K. Jia, C. Qing and D. Tao, "DehazeNet: An End-to-End System for Single Image Haze Removal," in IEEE Transactions on Image Processing, vol. 25, no. 11, pp. 5187-5198, Nov. 2016, doi: 10.1109/TIP.2016.2598681.
[13] K. Yan, L. Liang, Z. Zhen, G. Wang, Y. Yang, “Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images,” in Applied Sciences, 2022, 12(11), 5420, https://doi.org/10.3390/app12115420.
[14] Y. -T. Peng, K. Cao and P. C. Cosman, "Generalization of the Dark Channel Prior for Single Image Restoration," in IEEE Transactions on Image Processing, vol. 27, no. 6, pp. 2856-2868, June 2018, doi: 10.1109/TIP.2018.2813092.
[15] Y. -T. Peng and P. C. Cosman, "Underwater Image Restoration Based on Image Blurriness and Light Absorption," in IEEE Transactions on Image Processing, vol. 26, no. 4, pp. 1579-1594, April 2017, doi: 10.1109/TIP.2017.2663846.
[16] J. Justin, A. Alexandre, and F. -F. Li, "Perceptual losses for real-time style transfer and super-resolution," in European conference on computer vision, 2016: Springer, pp. 694-711.
[17] X. Fu, P. Zhuang, Y. Huang, Y. Liao, X. -P. Zhang and X. Ding, "A retinex-based enhancing approach for single underwater image," in 2014 IEEE International Conference on Image Processing (ICIP), Paris, France, 2014, pp. 4572-4576, doi: 10.1109/ICIP.2014.7025927.
[18] D. P. Kingma, and J. Ba, Kingma, D.P., & Ba, J. (2014). "Adam: A Method for Stochastic Optimization, " in CoRR, abs/1412.6980.
[19] K. Panetta, C. Gao and S. Agaian, "Human-Visual-System-Inspired Underwater Image Quality Measures," in IEEE Journal of Oceanic Engineering, vol. 41, no. 3, pp. 541-551, July 2016, doi: 10.1109/JOE.2015.2469915.
[20] M. Yang and A. Sowmya, "An Underwater Color Image Quality Evaluation Metric," in IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 6062-6071, Dec. 2015, doi: 10.1109/TIP.2015.2491020.
[21] 玩世科技(2017). Dive+, Suite 201, Bidg. A, 1 Qian-Wan 1st Rd., Qianhai Shenzhen-Houng Koung Cooperation District, Shenzhen,China. Accessed on: Jan. 9, 2024. [Online]. Availabe: http://dive.plus/
[22] A. Irfan(2020, April.). Deep Learning: An Overview of Convolutional Neural Network(CNN). Tampere University. Accessed on: Jan. 9, 2024. [Online]. Availabe: https://trepo.tuni.fi/bitstream/handle/10024/121936/AzizIrfan.pdf?sequence=2&isAllowed=y
[23] C. G. Rafael and E. W. Richard, Digital Image Processing, 4/e (GE-Paperback). 4th ed. Pearson FT Press, 2017
[24] F. Guo, J. Yang, Z. Liu, and J. Tang, Haze removal for single image: A comprehensive review. in Neurocomputing, 2023, 537, 85–109.
[25] Q. Wang and R. K. Ward, "Fast Image/Video Contrast Enhancement Based on Weighted Thresholded Histogram Equalization," in IEEE Transactions on Consumer Electronics, vol. 53, no. 2, pp. 757-764, May 2007, doi: 10.1109/TCE.2007.381756.