Style-Decoupled Adaptive Routing Network for Underwater Image Enhancement

TL;DR

This paper introduces SDAR-Net, an adaptive underwater image enhancement framework that decouples degradation styles and uses an adaptive routing mechanism to improve restoration quality, outperforming existing methods.

Contribution

The paper proposes a novel style-decoupled adaptive enhancement framework with an adaptive routing mechanism for underwater images, achieving state-of-the-art performance.

Findings

Achieved a PSNR of 25.72 dB on real-world benchmark

Outperformed existing methods in underwater image enhancement

Demonstrated utility in downstream vision tasks

Abstract

Underwater Image Enhancement (UIE) is essential for robust visual perception in marine applications. However, existing methods predominantly rely on uniform mapping tailored to average dataset distributions, leading to over-processing mildly degraded images or insufficient recovery for severe ones. To address this challenge, we propose a novel adaptive enhancement framework, SDAR-Net. Unlike existing uniform paradigms, it first decouples specific degradation styles from the input and subsequently modulates the enhancement process adaptively. Specifically, since underwater degradation primarily shifts the appearance while keeping the scene structure, SDAR-Net formulates image features into dynamic degradation style embeddings and static scene structural representations through a carefully designed training framework. Subsequently, we introduce an adaptive routing mechanism. By evaluating style features and adaptively predicting soft weights at different enhancement states, it guides the weighted fusion of the corresponding image representations, accurately satisfying the adaptive restoration demands of each image. Extensive experiments show that SDAR-Net achieves a new state-of-the-art (SOTA) performance with a PSNR of 25.72 dB on real-world benchmark, and demonstrates its utility in downstream vision tasks. Our code is available at https://github.com/WHU-USI3DV/SDAR-Net.