提出三阶段网络ADR，提升水下图像清晰度与视觉质量。
An Attention-Enhanced Network with Joint Dehazing and Retinex-Based Enhancement for Underwater Images
- 融合物理模型与深度学习，分步处理去雾、Retinex增强与注意力优化。
- 在UIEB和UFO-120数据集上优于现有方法，显著改善水下图像视觉效果。
- 适合水下机器人、海洋生物等需要高质量图像的应用场景。
水下图像因波长相关的光吸收与散射、悬浮颗粒导致的浑浊而严重退化，影响自主水下航行器（AUV）、海洋生物学、考古学及海上基础设施检测等应用。传统图像形成模型难以捕捉非线性水下光照特性，纯数据驱动方法缺乏物理可解释性。本文提出一种三阶段网络ADR，通过扩展水下图像形成模型并引入额外项，依次实现水下去雾、基于Retinex的增强以及注意力增强型U-Net++精修。在UIEB和UFO-120基准数据集上的实验表明，该方法性能优于当前最优方法。
原文摘要 · Abstract (English)
Underwater images suffer from severe wavelength-dependent light absorption and scattering, and turbidity due to suspended particles, degrading visual quality for applications in autonomous underwater vehicles (AUVs), marine biology, archaeology, and offshore infrastructure inspection. Classical IFM inadequately capture nonlinear underwater light behavior, while purely data-driven methods lack physical interpretability. This paper proposes a three-stage network named ADR, that extends the underwater image formation model with additional terms to perform underwater dehazing, followed by Retinex-based enhancement and attention-enabled U-Net++ refinement. Experiments on UIEB and UFO-120 benchmark datasets demonstrate competitive performance with state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。