Underwater Image Enhancement with an Adaptive Self Supervised Network

High-quality underwater images are a vital source of modern marine vision and multimedia applications. But low visibility with color and contrast distortions in uneven underwater illumination conditions poses several challenges to these applications (e.g., visual servoing, long-range navigation, unmanned underwater vehicles, and SONAR imaging, etc.) working in robust conditions from dawn to dusk. Direct enhancement deteriorates the structure and texture with objectionable color casts due to distance-dependent attenuation and light scattering. This paper presents an adaptive self-supervised network for underwater image enhancement (ASSU-Net), which can work without relying on the type and quantity of training images, rather, it is capable of working with only a few input images. In this network, we split the image into reflection and illumination components to simplify the solution space, allowing us to handle the artifacts associated with each component independently. A structure and texture awareness scheme is introduced while following the mutual consistency of decomposition in combination with the histogram distribution. This scheme is embedded in the network to constrain objectionable artifacts (i.e., structure texture and edge distortions). The network loss is optimized to force the network to learn with a few shots of unpaired data, where we preserve visual details for low-lit underwater images. Extensive experiments are performed to demonstrate the superiority of the proposed method.