Underwater Image Restoration via Polymorphic Large Kernel CNNs

2024-12-24

AI Summary

To address severe blur degradation in underwater images, high computational overhead of existing methods, and insufficient semantic exploitation in the frequency domain, this paper proposes UIR-PolyKernel—a lightweight, pure-CNN architecture. Its key contributions are: (1) the first multi-scale and multi-shape large-kernel convolution ensemble, enabling efficient modeling of long-range spatial dependencies; (2) a Hybrid Domain Attention module jointly operating in frequency and spatial domains, leveraging FFT to explicitly capture semantically critical yet human-eye-invisible frequency features; and (3) complete elimination of attention mechanisms and nonlinear upsampling, ensuring low parameter count and high inference efficiency. Evaluated on multiple underwater benchmark datasets, UIR-PolyKernel achieves state-of-the-art PSNR and SSIM with significantly fewer FLOPs. It outperforms mainstream Transformer-based and heavy CNN models in visual restoration quality, striking an optimal balance among accuracy, generalization, and deployment efficiency.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Underwater Image Restoration (UIR) remains a challenging task in computer vision due to the complex degradation of images in underwater environments. While recent approaches have leveraged various deep learning techniques, including Transformers and complex, parameter-heavy models to achieve significant improvements in restoration effects, we demonstrate that pure CNN architectures with lightweight parameters can achieve comparable results. In this paper, we introduce UIR-PolyKernel, a novel method for underwater image restoration that leverages Polymorphic Large Kernel CNNs. Our approach uniquely combines large kernel convolutions of diverse sizes and shapes to effectively capture long-range dependencies within underwater imagery. Additionally, we introduce a Hybrid Domain Attention module that integrates frequency and spatial domain attention mechanisms to enhance feature importance. By leveraging the frequency domain, we can capture hidden features that may not be perceptible to humans but are crucial for identifying patterns in both underwater and on-air images. This approach enhances the generalization and robustness of our UIR model. Extensive experiments on benchmark datasets demonstrate that UIR-PolyKernel achieves state-of-the-art performance in underwater image restoration tasks, both quantitatively and qualitatively. Our results show that well-designed pure CNN architectures can effectively compete with more complex models, offering a balance between performance and computational efficiency. This work provides new insights into the potential of CNN-based approaches for challenging image restoration tasks in underwater environments. The code is available at href{https://github.com/CXH-Research/UIR-PolyKernel}{https://github.com/CXH-Research/UIR-PolyKernel}.

Problem

• Underwater Image Enhancement
• Visual Clarity
• Image Quality

Innovation

• UIR-PolyKernel
• Mixed Attention Module
• Efficient Underwater Image Restoration