arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2412.18459cs.CVeess.IV

基于多态大核CNN的水下图像恢复

Underwater Image Restoration via Polymorphic Large Kernel CNNs

University of Macau（澳门大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen Polytechnic University（深圳职业技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））

Xiaojiao Guo, Yihang Dong, Xuhang Chen, Weiwen Chen, Zimeng Li, FuChen Zheng, Chi-Man Pun

备注：
Accepted by ICASSP2025
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出UIR-PolyKernel水下图像恢复方法，利用多态大核CNN捕获长距离依赖，并结合混合域注意力模块增强特征表示，以轻量级纯CNN架构实现了最先进的恢复性能与计算效率的平衡。

摘要：

水下图像恢复（UIR）由于水下环境中图像退化的复杂性，仍然是计算机视觉中的一项具有挑战性的任务。尽管最近的方法利用了各种深度学习技术，包括Transformers和复杂的、参数量大的模型，在恢复效果上取得了显著改进，但我们证明了具有轻量级参数的纯CNN架构能够取得可比的结果。在本文中，我们提出了UIR-PolyKernel，这是一种利用多态大核CNN进行水下图像恢复的新方法。我们的方法独特地结合了不同尺寸和形状的大核卷积，以有效捕获水下图像中的长距离依赖关系。此外，我们引入了混合域注意力模块，该模块集成了频域和空域注意力机制以增强特征重要性。通过利用频域，我们能够捕获人类可能无法感知但对识别水下和空气中图像模式至关重要的隐藏特征。这种方法增强了我们UIR模型的泛化能力和鲁棒性。在基准数据集上的大量实验表明，UIR-PolyKernel在定量和定性方面均实现了水下图像恢复任务的最先进性能。我们的结果表明，设计良好的纯CNN架构能够有效地与更复杂的模型竞争，在性能和计算效率之间提供平衡。这项工作为基于CNN的方法在挑战性水下环境图像恢复任务中的潜力提供了新见解。代码可在https://github.com/CXH-Research/UIR-PolyKernel获取。

英文摘要：

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}.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑