提出隐式估计透射率的水下去雾网络，兼顾物理可解释性与视觉质量。
An Underwater Dehazing Network with Implicit Transmission Estimation
- 通过可学习衰减系数隐式估计深度，结合贝叶-朗伯定律计算各通道透射率
- 在UIEB和UFO-120数据集上表现优于传统方法，参数量约0.9M
- 适合需要物理合理性和高图像质量的水下视觉任务
水下图像受波长相关光吸收与散射影响，导致视觉质量下降，限制了自主水下航行器、海洋勘测及海上检测系统的可靠性。纯经典方法在真实数据集上性能不佳，而纯数据驱动方法缺乏物理可解释性。本文提出UDehaze-iT，一种用于水下图像增强的深度网络，通过可学习的衰减系数隐式估计场景深度，并利用贝叶-朗伯定律推导各通道透射率。大气光以每通道半经典标量形式估计，零初始化残差修正器用于消除去雾后残留伪影。为有效训练，采用包含五项关键项的复合损失函数：L1损失、多尺度块状DCT损失、前向模型重建损失及两项正则化项。该模型拥有约0.9M参数，在UIEB和UFO-120数据集上取得竞争性性能。
原文摘要 · Abstract (English)
Underwater images suffer from wavelength-dependent light absorption and scattering, which reduces visual quality. This phenomenon could limit the operational reliability of autonomous underwater vehicles, marine surveys, and offshore inspection systems. Purely classical methods often achieve suboptimal performance in real-world datasets, while purely data-driven methods lack physical interpretability. In this letter, we propose UDehaze-iT, a deep network for underwater image enhancement that estimates scene depth implicitly and derives per-channel transmission through the Beer-Lambert law with learnable attenuation coefficients. We estimate atmospheric light as a semi-classical per-channel scalar, and a zero-initialized residual refiner corrects remaining artefacts after dehazing. To effectively train our method, we apply a composite loss function consisting of five key terms: a L1 loss, a multi-scale patchwise DCT loss, a forward model reconstruction loss, and two regularization terms. With ~0.9M parameters, UDehaze-iT achieves competitive performance on UIEB and UFO-120 datasets.
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。