人類對海洋的探索仍然非常有限，海洋覆蓋地球70%的表面，但已探測區域僅約5%。深海的壓力、溫度及光線都是造成探索困難的原因。儘管已取得深海影像，但因影像品質不佳而可能影響科學研究的結果。因此，水下影像還原是人類探索海洋的一項重要技術，對於水下任務提供更可靠的基礎，推動海洋科學的進展。
光線在水下傳播時，會受到水中懸浮粒子的吸收與散射影響，造成影像模糊不清、亮度降低或呈現藍綠色偏，使得影像的應用價值降低。為了恢復水下影像品質，有許多水下影像還原方法被提出，已經能達到不錯的還原效果。
近年由於硬體效能的快速進步，推動了深度學習在影像強化領域的研究。過去，影像強化大多是根據人們對於問題的觀察設計先驗 （Prior），並根據先驗還原影像。這類型的方法能夠快速地計算出影像，但經常只能處理特定的退化類型，泛化能力較差。深度學習方法基於輸入的數據訓練模型，讓模型自己學習各種退化模式的還原方法，大幅提升了對複雜且多樣化退化的處理能力。
本論文基於深度學習方法 Zero-Restore 的自監督框架，設計水下影像還原的方法，並在特徵空間使用 Koschmieder 光學散射模型進行合成，能夠保留更多的影像細節，避免影像過度強化，並引入通道注意力與空間注意力機制，使模型能夠更好的從特徵中提取出重要的資訊，有助於提升水下影像品質。

Aupendu Kar et al. “Zero-Shot Single Image Restoration Through Controlled Perturbation of Koschmieder’s Model”. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 2021, pp. 16205–16215.
H. Koschmieder. Theorie der horizontalen Sichtweite. Beiträge zur Physik der freien Atmosphäre. Keim & Nemnich, 1924.
Sanghyun Woo et al. “CBAM: Convolutional block attention module”. In: Proceedings of the European conference on computer vision (ECCV). 2018, pp. 3–19.
Yan-Tsung Peng, Keming Cao, and Pamela C. Cosman. “Generalization of the Dark Channel Prior for Single Image Restoration”. In: IEEE Transactions on Image Processing 27.6 (2018), pp. 2856–2868. DOI: 10.1109/TIP.2018.2813092.
Peixian Zhuang et al. “Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors”. In: IEEE Transactions on Image Processing 31 (2022), pp. 5442–5455. DOI:10.1109/TIP.2022.3196546.
Yan-Tsung Peng and Pamela C. Cosman. “Underwater Image Restoration Based on Image Blurriness and Light Absorption”. In: IEEE Transactions on Image Processing 26.4 (2017), pp. 1579–1594. DOI: 10.1109/TIP.2017.2663846.
Chongyi Li et al. “An Underwater Image Enhancement Benchmark Dataset and Beyond”. In: IEEE Transactions on Image Processing 29 (2020), pp. 4376–4389. DOI: 10.1109/TIP.2019.2955241.
Wangzhen Peng et al. RAUNE-Net: A Residual and Attention-Driven Underwater Image Enhancement Method. 2023. arXiv: 2311.00246 [cs.CV].
Md Jahidul Islam, Youya Xia, and Junaed Sattar. “Fast Underwater Image Enhancement for Improved Visual Perception”. In: IEEE Robotics and Automation Letters 5.2 (2020), pp. 3227–3234. DOI: 10.1109/LRA.2020.2974710.
Yosef Gandelsman, Assaf Shocher, and Michal Irani. “Double-DIP: unsupervised image decomposition via coupled deep-image-priors”. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. June 2019, pp. 11026–11035.
Gershon Buchsbaum. “A spatial processor model for object colour perception”. In: Journal of The Franklin Institute-engineering and Applied Mathematics 310 (1980), pp. 1–26.
Paul Rodríguez. “Total variation regularization algorithms for images corrupted with different noise models: a review”. In: Journal of Electrical and Computer Engineering 2013.1 (2013), p. 217021. DOI: 10.1155/2013/217021.
Fu-Jen Tsai et al. “PHATNet: A Physics-guided Haze Transfer Network for Domain adaptive Real-world Image Dehazing”. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Oct. 2025, pp. 5591–5600.
Risheng Liu et al. “Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light”. In: IEEE Transactions on Circuits and Systems for Video Technology 30.12 (2020), pp. 4861–4875. DOI: 10.1109/TCSVT.2019.2963772.
Hanyu Li, Jingjing Li, and Wei Wang. A Fusion Adversarial Underwater Image Enhancement Network with a Public Test Dataset. 2019. arXiv: 1906.06819.
Xueyang Fu et al. “A retinex-based enhancing approach for single underwater image”. In: 2014 IEEE International Conference on Image Processing (ICIP). 2014.
Cosmin Ancuti et al. “Enhancing underwater images and videos by fusion”. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012.
Adrian Galdran et al. “Automatic Red-Channel underwater image restoration”. In: Journal of Visual Communication and Image Representation 26 (2015), pp. 132–145. ISSN: 1047-3203. DOI: 10.1016/j.jvcir.2014.11.006.
Cameron Fabbri, Md Jahidul Islam, and Junaed Sattar. “Enhancing Underwater Imagery Using Generative Adversarial Networks”. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). 2018.
Olga Russakovsky et al. ImageNet Large Scale Visual Recognition Challenge. 2015. arXiv: 1409.0575 [cs.CV].
Jianxiong Xiao et al. “SUN database: Large-scale scene recognition from abbey to zoo”. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2010.
Karen Panetta, Chen Gao, and Sos Agaian. “Human-Visual-System-Inspired Underwater Image Quality Measures”. In: IEEE Journal of Oceanic Engineering 41.3 (2016), pp. 541–551. DOI: 10.1109/JOE.2015.2469915.
Miao Yang and Arcot Sowmya. “An Underwater Color Image Quality Evaluation Metric”. In: IEEE Transactions on Image Processing 24.12 (2015), pp. 6062–6071. DOI: 10.1109/TIP.2015.2491020.
Shiqi Wang et al. “A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images”. In: IEEE Signal Processing Letters 22.12 (2015), pp. 2387–2390. DOI: 10.1109/LSP.2015.2487369.
Richard Zhang et al. “The Unreasonable Effectiveness of Deep Features as a Perceptual Metric”. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, pp. 586–595. DOI: 10.1109/CVPR.2018.00068.
Karen Simonyan and Andrew Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2015. arXiv: 1409.1556 [cs.CV].
Codruta O Ancuti et al. “O-haze: a dehazing benchmark with real hazy and haze-free outdoor images”. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2018.