CoRe-UIE: Rethinking Coexisting and Region-wise Degradation for Underwater Image Enhancement

2026-08-09

AI Summary

Underwater images often suffer from spatially heterogeneous degradations, including color distortion, scattering-induced haze, texture attenuation, and uneven illumination, which challenge conventional uniform restoration approaches. To address this, this work proposes a degradation-aware collaborative expert framework that employs a shared backbone network coupled with four specialized experts—dedicated respectively to color correction, scattering suppression, texture recovery, and illumination preservation. A region-adaptive Top-k routing mechanism, guided by input degradation cues, enables precise modeling of diverse image regions. Furthermore, Hilbert-Schmidt Independence Criterion (HSIC) constraints are imposed on expert features to minimize response redundancy. The proposed method achieves state-of-the-art quantitative performance on the UIEB, LSUI, and U45 benchmarks and demonstrates visually balanced enhancement across diverse underwater scenes.

Abstract

Underwater images often suffer from diverse and coexisting degradations, including color distortion, scattering haze, texture attenuation, and uneven illumination. These degradations vary across regions and may coexist locally, making conventional uniform restoration difficult to adapt to different degradation patterns. To address this problem, we propose Coexisting and Region-wise Degradation for Underwater Image Enhancement (\textbf{CoRe-UIE}), a degradation-oriented expert collaboration framework. CoRe-UIE combines a content-preserving shared expert with four shared-backbone routed experts for color correction, scattering suppression, texture recovery, and illumination protection. The routed experts share the same architecture but have independent parameters, and are assigned to different regions through input-derived degradation cues and region-adaptive Top-\(k\) routing. We further introduce a Hilbert--Schmidt Independence Criterion (HSIC)-based representation constraint to reduce statistical dependence among expert features and alleviate redundant expert responses. Experiments on UIEB, LSUI, and U45 demonstrate that CoRe-UIE achieves competitive quantitative performance and visually balanced enhancement under diverse underwater degradation conditions.

Problem

• underwater image enhancement
• coexisting degradations
• region-wise degradation
• color distortion
• scattering haze

Innovation

• expert collaboration
• region-wise routing
• degradation-aware enhancement
• HSIC regularization
• underwater image enhancement