DACA-Net: A Degradation-Aware Conditional Diffusion Network for Underwater Image Enhancement

2025-07-30

AI Summary

Underwater images suffer from severe color distortion, low contrast, and structural blurring due to light scattering and absorption; existing methods struggle to adaptively handle diverse degradations and lack explicit physical prior modeling. To address this, we propose Degradation-Aware Conditional Diffusion (DADiff), the first framework integrating degradation-level prediction with physics-informed conditional diffusion modeling. Specifically, we design a lightweight dual-stream convolutional network to estimate degradation scores, adopt a Swin UNet-based architecture as the conditional diffusion backbone, and introduce a degradation-guided feature fusion module. We jointly optimize a hybrid loss combining perceptual consistency, histogram matching, and feature-level contrastive learning. Extensive experiments on multiple benchmark datasets demonstrate that DADiff achieves state-of-the-art performance in color fidelity, visual quality, and fine-detail recovery—validated by both quantitative metrics and subjective evaluation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Underwater images typically suffer from severe colour distortions, low visibility, and reduced structural clarity due to complex optical effects such as scattering and absorption, which greatly degrade their visual quality and limit the performance of downstream visual perception tasks. Existing enhancement methods often struggle to adaptively handle diverse degradation conditions and fail to leverage underwater-specific physical priors effectively. In this paper, we propose a degradation-aware conditional diffusion model to enhance underwater images adaptively and robustly. Given a degraded underwater image as input, we first predict its degradation level using a lightweight dual-stream convolutional network, generating a continuous degradation score as semantic guidance. Based on this score, we introduce a novel conditional diffusion-based restoration network with a Swin UNet backbone, enabling adaptive noise scheduling and hierarchical feature refinement. To incorporate underwater-specific physical priors, we further propose a degradation-guided adaptive feature fusion module and a hybrid loss function that combines perceptual consistency, histogram matching, and feature-level contrast. Comprehensive experiments on benchmark datasets demonstrate that our method effectively restores underwater images with superior colour fidelity, perceptual quality, and structural details. Compared with SOTA approaches, our framework achieves significant improvements in both quantitative metrics and qualitative visual assessments.

Problem

• Enhance underwater images with color distortion and low visibility
• Adaptively handle diverse underwater degradation conditions
• Incorporate underwater-specific physical priors effectively

Innovation

• Lightweight dual-stream network predicts degradation level
• Conditional diffusion model with Swin UNet backbone
• Degradation-guided adaptive feature fusion module