WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement

2025-11-20

AI Summary

Underwater image enhancement (UIE) suffers from visibility degradation and severe color casts due to wavelength-dependent absorption and scattering. While existing hybrid methods achieve strong performance, their high computational complexity impedes real-time deployment. To address this, we propose an efficient and interpretable lightweight UIE network. First, an adaptive white balance module corrects global color bias. Second, a wavelet-domain multi-band decomposition jointly models frequency-domain details and spatial edge structures via a learnable gated Sobel gradient perception module. Third, a compact neural architecture enables end-to-end optimization. Extensive experiments on multiple benchmarks demonstrate state-of-the-art visual quality with remarkably low model complexity—≤0.52M parameters and ≤1.8G FLOPs—enabling real-time inference on embedded devices. Ablation studies validate the effectiveness and synergistic gains of each prior-guided module.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Mixture of Experts (MoE)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Underwater Image Enhancement (UIE) aims to restore visibility and correct color distortions caused by wavelength-dependent absorption and scattering. Recent hybrid approaches, which couple domain priors with modern deep neural architectures, have achieved strong performance but incur high computational cost, limiting their practicality in real-time scenarios. In this work, we propose WWE-UIE, a compact and efficient enhancement network that integrates three interpretable priors. First, adaptive white balance alleviates the strong wavelength-dependent color attenuation, particularly the dominance of blue-green tones. Second, a wavelet-based enhancement block (WEB) performs multi-band decomposition, enabling the network to capture both global structures and fine textures, which are critical for underwater restoration. Third, a gradient-aware module (SGFB) leverages Sobel operators with learnable gating to explicitly preserve edge structures degraded by scattering. Extensive experiments on benchmark datasets demonstrate that WWE-UIE achieves competitive restoration quality with substantially fewer parameters and FLOPs, enabling real-time inference on resource-limited platforms. Ablation studies and visualizations further validate the contribution of each component. The source code is available at https://github.com/chingheng0808/WWE-UIE.

Problem

• Reducing computational costs in underwater image enhancement
• Correcting color distortions from wavelength-dependent absorption
• Preserving edge structures degraded by underwater scattering

Innovation

• Adaptive white balance corrects color attenuation
• Wavelet-based block captures global and fine details
• Gradient-aware module preserves edges with learnable gating