Enhancing Underwater Images via Adaptive Semantic-aware Codebook Learning

TL;DR

This paper introduces SUCode, a semantic-aware codebook learning approach for underwater image enhancement that adaptively restores color and details by considering regional degradation differences.

Contribution

It proposes a novel semantic-aware, pixel-level codebook representation and a three-stage training paradigm for improved underwater image enhancement.

Findings

SUCode outperforms existing methods on multiple benchmarks.

It achieves state-of-the-art results in both reference and no-reference metrics.

The approach effectively restores color and texture details in heterogeneous underwater scenes.

Abstract

Underwater Image Enhancement (UIE) is an ill-posed problem where natural clean references are not available, and the degradation levels vary significantly across semantic regions. Existing UIE methods treat images with a single global model and ignore the inconsistent degradation of different scene components. This oversight leads to significant color distortions and loss of fine details in heterogeneous underwater scenes, especially where degradation varies significantly across different image regions. Therefore, we propose SUCode (Semantic-aware Underwater Codebook Network), which achieves adaptive UIE from semantic-aware discrete codebook representation. Compared with one-shot codebook-based methods, SUCode exploits semantic-aware, pixel-level codebook representation tailored to heterogeneous underwater degradation. A three-stage training paradigm is employed to represent raw underwater image features to avoid pseudo ground-truth contamination. Gated Channel Attention Module (GCAM) and Frequency-Aware Feature Fusion (FAFF) jointly integrate channel and frequency cues for faithful color restoration and texture recovery. Extensive experiments on multiple benchmarks demonstrate that SUCode achieves state-of-the-art performance, outperforming recent UIE methods on both reference and no-reference metrics. The code will be made public available at https://github.com/oucailab/SUCode.