Li Tengyue, Yang Qianqian, Rong Shenghui, Chen Long, He Bo
Appl Opt. 2020 Nov 10;59(32):10049-10060. doi: 10.1364/AO.402024.
Imaging through the wavy air-water surface suffers from severe geometric distortions, which are caused by the light refraction effect that affects the normal operations of underwater exploration equipment such as the autonomous underwater vehicle (AUV). In this paper, we propose a deep learning-based framework, namely the self-attention generative adversarial network (SAGAN), to remove the geometric distortions and restore the distorted image captured through the water-air surface. First, a K-means-based image pre-selection method is employed to acquire a less distorted image that preserves much useful information from an image sequence. Second, an improved generative adversarial network (GAN) is trained to translate the distorted image into the non-distorted image. During this process, the attention mechanism and the weighted training objective are adopted in our GAN framework to get the high-quality restored results of distorted underwater images. The network is able to restore the colors and fine details in the distorted images by combining the three objective losses, i.e., the content loss, the adversarial loss, and the perceptual loss. Experimental results show that our proposed method outperforms other state-of-the-art methods on the validation set and our sea trial set.
通过波浪起伏的空气-水面进行成像会遭受严重的几何失真，这是由光折射效应引起的，该效应会影响水下探测设备（如自主水下航行器（AUV））的正常运行。在本文中，我们提出了一种基于深度学习的框架，即自注意力生成对抗网络（SAGAN），以消除几何失真并恢复通过水-气表面捕获的失真图像。首先，采用基于K均值的图像预选择方法，从图像序列中获取失真较小且保留了许多有用信息的图像。其次，训练一个改进的生成对抗网络（GAN），将失真图像转换为不失真图像。在此过程中，我们的GAN框架采用了注意力机制和加权训练目标，以获得高质量的水下失真图像恢复结果。该网络通过结合内容损失、对抗损失和感知损失这三种目标损失，能够恢复失真图像中的颜色和精细细节。实验结果表明，我们提出的方法在验证集和海上试验集上优于其他现有方法。
