论文标题
基于物理模型反馈的域自适应对抗学习，用于水下图像增强
Domain Adaptive Adversarial Learning Based on Physics Model Feedback for Underwater Image Enhancement
论文作者
论文摘要
由于水中悬浮颗粒的折射，吸收和光散射，因此原始的水下图像遭受了较低的对比度，模糊的细节和颜色失真。这些特征可以显着干扰水下图像的可见性以及视觉任务的结果，例如分割和跟踪。为了解决这个问题，我们通过基于物理模型的反馈控制和域适应机制提出了一个新的强大对抗学习框架，以增强水下图像以获得现实结果。提出了一种通过水下图像形成模型从RGB-D数据中模拟水下样训练数据集的新方法。在合成数据集时，训练了一种新颖的增强框架，它引入了域自适应机制以及物理模型约束反馈控制，以增强水下场景。关于合成和实际水下图像的最终增强结果证明了所提出的方法的优越性，该方法在定性和定量评估中均优于nondeep和深度学习方法。此外，我们进行了一项消融研究，以显示我们提出的每个组件的贡献。
Owing to refraction, absorption, and scattering of light by suspended particles in water, raw underwater images suffer from low contrast, blurred details, and color distortion. These characteristics can significantly interfere with the visibility of underwater images and the result of visual tasks, such as segmentation and tracking. To address this problem, we propose a new robust adversarial learning framework via physics model based feedback control and domain adaptation mechanism for enhancing underwater images to get realistic results. A new method for simulating underwater-like training dataset from RGB-D data by underwater image formation model is proposed. Upon the synthetic dataset, a novel enhancement framework, which introduces a domain adaptive mechanism as well as a physics model constraint feedback control, is trained to enhance the underwater scenes. Final enhanced results on synthetic and real underwater images demonstrate the superiority of the proposed method, which outperforms nondeep and deep learning methods in both qualitative and quantitative evaluations. Furthermore, we perform an ablation study to show the contributions of each component we proposed.
