WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images
This work addresses the challenge of restoring underwater images for autonomous and remotely operated vehicles, which is crucial for seafloor mapping, but it is incremental as it builds on existing GAN methods to handle domain-specific data scarcity.
The paper tackles the problem of color correction for monocular underwater images, which are degraded by light absorption and scattering, by introducing WaterGAN, an unsupervised generative network that generates realistic underwater images from in-air images and depth data to create a large training dataset, enabling real-time color correction with results validated on real data from water tanks and field surveys.
This paper reports on WaterGAN, a generative adversarial network (GAN) for generating realistic underwater images from in-air image and depth pairings in an unsupervised pipeline used for color correction of monocular underwater images. Cameras onboard autonomous and remotely operated vehicles can capture high resolution images to map the seafloor, however, underwater image formation is subject to the complex process of light propagation through the water column. The raw images retrieved are characteristically different than images taken in air due to effects such as absorption and scattering, which cause attenuation of light at different rates for different wavelengths. While this physical process is well described theoretically, the model depends on many parameters intrinsic to the water column as well as the objects in the scene. These factors make recovery of these parameters difficult without simplifying assumptions or field calibration, hence, restoration of underwater images is a non-trivial problem. Deep learning has demonstrated great success in modeling complex nonlinear systems but requires a large amount of training data, which is difficult to compile in deep sea environments. Using WaterGAN, we generate a large training dataset of paired imagery, both raw underwater and true color in-air, as well as depth data. This data serves as input to a novel end-to-end network for color correction of monocular underwater images. Due to the depth-dependent water column effects inherent to underwater environments, we show that our end-to-end network implicitly learns a coarse depth estimate of the underwater scene from monocular underwater images. Our proposed pipeline is validated with testing on real data collected from both a pure water tank and from underwater surveys in field testing. Source code is made publicly available with sample datasets and pretrained models.