Style-Decoupled Adaptive Routing Network for Underwater Image Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Hang, Long, Chen, Wang, Bing, Chen, Hao, Dong, Zhen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908961982119936
author Xu, Hang
Long, Chen
Wang, Bing
Chen, Hao
Dong, Zhen
author_facet Xu, Hang
Long, Chen
Wang, Bing
Chen, Hao
Dong, Zhen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12257
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Style-Decoupled Adaptive Routing Network for Underwater Image Enhancement
Xu, Hang
Long, Chen
Wang, Bing
Chen, Hao
Dong, Zhen
Computer Vision and Pattern Recognition
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.
title Style-Decoupled Adaptive Routing Network for Underwater Image Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.12257