CLUIE: Clustering-Aware Recurrent Propagation with Local Structural Compensation for Underwater Image Enhancement

2026-07-23

AI Summary

Underwater images suffer from severe color distortion, contrast degradation, and detail loss due to wavelength-dependent absorption and scattering, with degradation patterns exhibiting strong spatial non-uniformity. To address this challenge, this work proposes the CRWKV framework, which introduces a novel clustering-aware semantic dynamic reordering (CSDR) mechanism to construct content-adaptive recursive propagation paths. It further integrates a dark response modulation local propagation (DMLP) strategy guided by pseudo-dark response maps, effectively fusing long-range semantic dependencies with local structural continuity. The method achieves adaptive restoration of spatially heterogeneous degradations while maintaining linear computational complexity, delivering state-of-the-art quantitative performance and superior visual quality across multiple underwater image enhancement benchmarks.

Abstract

Underwater image enhancement remains challenging due to wavelength-dependent light absorption, scattering, and backscattering, which jointly cause color distortion, contrast degradation, and detail loss. Since these degradations vary with scene depth and imaging conditions, different regions within the same image often exhibit heterogeneous degradation patterns and thus require region-adaptive restoration. Although visual RWKV models offer an efficient linear-complexity solution for long-range dependency modeling, their predefined scanning orders are content-agnostic and therefore fail to adapt recurrent state propagation to spatially non-uniform restoration demands. To address this limitation, we propose a Clustering-aware RWKV framework, termed CRWKV, which reformulates the fixed recurrent propagation path of conventional RWKV into a content-adaptive token trajectory. Specifically, we introduce Clustering-aware Semantic Dynamic Reordering (CSDR), which groups tokens according to semantic feature similarity and derives a dynamic traversal order from inter-cluster contextual relations. This design enables WKV states to be accumulated along semantically correlated regions rather than fixed spatial or spectral orders. Since dynamic reordering may disrupt the local continuity of original spatial neighborhoods, we further propose Dark-response Modulated Local Propagation (DMLP), which extracts local structural responses via depth-wise convolution and adaptively modulates their propagation strength using a neighborhood-aware pseudo-dark response map. In this way, local structural cues are compensated before recurrent aggregation while preserving content-adaptive long-range modeling. Extensive experiments on multiple underwater image enhancement benchmarks demonstrate that CRWKV achieves state-of-the-art quantitative performance and superior visual quality.

Problem

• underwater image enhancement
• color distortion
• contrast degradation
• detail loss
• region-adaptive restoration

Innovation

• Clustering-aware RWKV
• Semantic Dynamic Reordering
• Local Structural Compensation
• Underwater Image Enhancement
• Recurrent Propagation