CoRe-UIE: Rethinking Coexisting and Region-wise Degradation for Underwater Image Enhancement
2026-08-10 • Artificial Intelligence
Artificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors developed CoRe-UIE, a system to improve underwater images that suffer from different problems like color issues, haze, and uneven lighting. Instead of treating the whole image the same, their method divides the image into regions and uses specialized experts focused on different issues to fix each part. These experts work together but handle separate tasks like color correction and texture recovery. The system also uses a technique to make sure the experts don't do overlapping work. Tests show their approach effectively improves underwater images in various situations.
underwater image enhancementcolor correctionscattering hazetexture recoveryillumination protectionregion-adaptive routingHilbert–Schmidt Independence Criterion (HSIC)image degradationdeep learning expertsUIEB dataset
Authors
Weifeng Kong, Chenghao Xu, Lin Chen, Ziheng Cao, Guanying Huo
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.