AQUA-Net: Adaptive Frequency Fusion and Illumination Aware Network for Underwater Image Enhancement

2025-12-05

AI Summary

Underwater images suffer from severe color distortion, low contrast, and blurriness due to wavelength-dependent absorption and scattering. Existing deep learning–based enhancement methods incur high computational overhead, hindering real-time deployment. To address this, we propose a lightweight underwater image enhancement network that innovatively integrates spatial-domain processing, frequency-domain analysis (via Fourier transform), and illumination-aware modeling. Specifically, we design a frequency-domain fusion encoder to extract multi-scale spectral features, develop a Retinex-inspired illumination-aware decoder for learnable illumination mapping and adaptive exposure correction, and incorporate dual auxiliary branches to strengthen detail recovery. Our model achieves significantly fewer parameters than state-of-the-art methods while matching or surpassing their performance on standard benchmarks (UIEB, EUVP). Furthermore, it demonstrates strong robustness and practical utility on a newly constructed deep-sea video dataset.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Underwater images often suffer from severe color distortion, low contrast, and a hazy appearance due to wavelength-dependent light absorption and scattering. Simultaneously, existing deep learning models exhibit high computational complexity, which limits their practical deployment for real-time underwater applications. To address these challenges, this paper presents a novel underwater image enhancement model, called Adaptive Frequency Fusion and Illumination Aware Network (AQUA-Net). It integrates a residual encoder decoder with dual auxiliary branches, which operate in the frequency and illumination domains. The frequency fusion encoder enriches spatial representations with frequency cues from the Fourier domain and preserves fine textures and structural details. Inspired by Retinex, the illumination-aware decoder performs adaptive exposure correction through a learned illumination map that separates reflectance from lighting effects. This joint spatial, frequency, and illumination design enables the model to restore color balance, visual contrast, and perceptual realism under diverse underwater conditions. Additionally, we present a high-resolution, real-world underwater video-derived dataset from the Mediterranean Sea, which captures challenging deep-sea conditions with realistic visual degradations to enable robust evaluation and development of deep learning models. Extensive experiments on multiple benchmark datasets show that AQUA-Net performs on par with SOTA in both qualitative and quantitative evaluations while using less number of parameters. Ablation studies further confirm that the frequency and illumination branches provide complementary contributions that improve visibility and color representation. Overall, the proposed model shows strong generalization capability and robustness, and it provides an effective solution for real-world underwater imaging applications.

Problem

• Enhances underwater images with color distortion and low contrast
• Reduces computational complexity for real-time underwater applications
• Restores color balance and details using frequency and illumination domains

Innovation

• Frequency fusion encoder enriches spatial representations with Fourier cues
• Illumination-aware decoder performs adaptive exposure correction via learned map
• Joint spatial, frequency, illumination design restores color balance and contrast