DTKD-Net: Dual-Teacher Knowledge Distillation Lightweight Network for Water-Related Optics Image Enhancement

Water-related optics images are often degraded by absorption and scattering effects. Current underwater image enhancement (UIE) methods improve image quality but neglect the constraints of underwater imaging environments. To address this issue, we propose a double-teacher knowledge distilling network (DTKD-Net), which uses a dynamic teaching strategy within a dual-teacher framework to enhance knowledge distillation (KD), improving the student network’s ability to capture complex underwater features. Specifically, DTKD-Net focuses on clear-to-clear and blurry-to-clear image learning to enhance underwater images. It aims to preserve details in clear images and restore blurred ones. The dual-teacher network uses an intermediate layer with the middle layer of the student network to compute feature differences for feature guidance. The network uses a dynamic strategy where a Teacher-Sub stops guidance when its output matches the student’s, which helps with contrastive learning and improves the network’s ability to handle complex underwater scenes. Extensive experiments and visual comparisons show that DTKD-Net reduces the model size, demonstrating superior efficiency and effectiveness in enhancing underwater images.

I. Introduction

Water-related optical imaging plays a crucial role in the exploration and utilization of marine resources [1], [2], [3]. These images contain rich marine information fundamental for exploring, developing, and protecting marine resources [4], [5], [6]. However, the unique conditions of underwater environments, such as light attenuation and water turbidity, often severely affect the clarity and quality of images, limiting our ability to observe and recognize important information, such as seabed structures, ecological distribution, and biological communities [7]. To address this challenge, researchers are focusing on underwater image enhancement (UIE) technologies. UIE methods significantly improve image quality and deepen our understanding of the marine environment, promoting the full utilization and effective protection of marine resources [8], [9]. The study of UIE holds significant academic value and broad application prospects, making it an important area of research from both theoretical and practical perspectives.