Task-Driven Underwater Image Enhancement via Hierarchical Semantic Refinement

Meng Yu, Liquan Shen, Yihan Yu, Yu Zhang, Rui Le

Abstract: Underwater image enhancement (UIE) is crucial for robust marine exploration, yet existing methods prioritize perceptual quality while overlooking irreversible semantic corruption that impairs downstream tasks. Unlike terrestrial images, underwater semantics exhibit layer-specific degradations: shallow features suffer from color shifts and edge erosion, while deep features face semantic ambiguity. These distortions entangle with semantic content across feature hierarchies, where direct enhancement amplifies interference in downstream tasks. Even if distortions are removed, the damaged semantic structures cannot be fully recovered, making it imperative to further enhance corrupted content. To address these challenges, we propose a task-driven UIE framework that redefines enhancement as machine-interpretable semantic recovery rather than mere distortion removal. First, we introduce a multi-scale underwater distortion-aware generator to perceive distortions across feature levels and provide a prior for distortion removal. Second, leveraging this prior and the absence of clean underwater references, we propose a stable self-supervised disentanglement strategy to explicitly separate distortions from corrupted content through CLIP-based semantic constraints and identity consistency. Finally, to compensate for the irreversible semantic loss, we design a task-aware hierarchical enhancement module that refines shallow details via spatial-frequency fusion and strengthens deep semantics through multi-scale context aggregation, aligning results with machine vision requirements. Extensive experiments on segmentation, detection, and saliency tasks demonstrate the superiority of our method in restoring machine-friendly semantics from degraded underwater images. Our code is available at https://github.com/gemyumeng/HSRUIE

External IDs:doi:10.1109/tip.2025.3647323