Deep Learning based Underwater Image Enhancement: A Review of Trends, Challenges, and Task Relevance
Abstract
Underwater images often suffer from significant quality degradation due to light absorption, scattering, suspended particles, low illumination, and color distortion, which limit their usability in marine applications. To address these challenges, deep learning-based methods, including Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), transformer-based architectures, and hybrid models, have been extensively developed to enhance visual quality by improving color consistency, contrast, and structural details. In this paper, we present a comprehensive review of these approaches and propose a unified taxonomy that systematically categorizes existing methods while highlighting recent advancements. In addition, we emphasize the emerging concept of task-aware enhancement, where image quality is evaluated based on its effectiveness in downstream tasks such as object detection, segmentation, and marine monitoring. This perspective is important as it bridges the gap between visual enhancement and practical application performance. Furthermore, we demonstrate that integrating multiple learning paradigms and adopting application-driven evaluation strategies can improve robustness and generalization. The findings suggest that hybrid and task-aware approaches are promising directions for developing efficient and reliable underwater image enhancement systems.