Semi-Supervised Underwater Image Enhancement Network Boosted by Depth Map Consistency

Underwater optical images are a crucial information source for autonomous underwater vehicles during underwater development and exploration. When these vehicles are in operation, they need to capture high-quality images for information extraction and analysis and require depth map information from the underwater scene to maintain the vehicle's posture balance, obstacle avoidance, and navigation. However, the absorption and scattering of light in water result in low-quality underwater images, significantly affecting the execution of these tasks. In response to these challenges, this article proposes a physically guided, semi-supervised dual-loop network for underwater image enhancement. This network is designed to accomplish high-quality underwater image enhancement and depth map estimation simultaneously. First, the revised underwater image formation model is employed to guide a two-stage network in decomposing and reconstructing underwater images. The depth map consistency of the scene and piecewise cycle consistency loss are utilized to ensure the reliability of the image transformation process. In another loop, a self-augmentation module based on inherent optical properties is introduced to enhance the robustness of the decomposition network. A multimodal discriminator is incorporated to form piecewise adversarial loss to improve the visual quality of the images. Through extensive experimental evaluation and analysis, the proposed method not only demonstrates outstanding performance in underwater image enhancement and depth map estimation but also reveals the relationships between various physical quantities during the degradation process of underwater images, enhancing the physical interpretability of the neural network.