Recently, Unsupervised algorithms has achieved remarkable performance in image dehazing. However, the CycleGAN framework can lead to confusion in generator learning due to inconsistent data distributions, and the DisentGAN framework lacks effective constraints on generated images, resulting in the loss of image content details and color distortion. Moreover, Squeeze and Excitation channel attention employs only fully connected layers to capture global information, lacking interaction with local information, resulting in inaccurate feature weight allocation for image dehazing. To solve the above problems, in this paper, we propose an Unsupervised Bidirectional Contrastive Reconstruction and Adaptive Fine-Grained Channel Attention Networks (UBRFC-Net). Specifically, an Unsupervised Bidirectional Contrastive Reconstruction Framework (BCRF) is proposed, aiming to establish bidirectional contrastive reconstruction constraints, not only to avoid the generator learning confusion in CycleGAN but also to enhance the constraint capability for clear images and the reconstruction ability of the unsupervised dehazing network. Furthermore, an Adaptive Fine-Grained Channel Attention (FCA) is developed to utilize the correlation matrix to capture the correlation between global and local information at various granularities promotes interaction between them, achieving more efficient feature weight assignment. Experimental results on challenging benchmark datasets demonstrate the superiority of our UBRFC-Net over state-of-the-art unsupervised image dehazing methods. This study successfully introduces an enhanced unsupervised image dehazing approach, addressing limitations of existing methods and achieving superior dehazing results. The source code is available at .

中文翻译：

---

用于图像去雾的无监督双向对比重建和自适应细粒度通道注意网络

近年来，无监督算法在图像去雾方面取得了显着的性能。然而，CycleGAN 框架会因数据分布不一致而导致生成器学习混乱，而 DisentGAN 框架缺乏对生成图像的有效约束，导致图像内容细节丢失和颜色失真。此外，挤压和激励通道注意力仅采用全连接层来捕获全局信息，缺乏与局部信息的交互，导致图像去雾的特征权重分配不准确。为了解决上述问题，在本文中，我们提出了一种无监督双向对比重建和自适应细粒度通道注意网络（UBRFC-Net）。具体来说，提出了一种无监督双向对比重建框架（BCRF），旨在建立双向对比重建约束，不仅可以避免CycleGAN中的生成器学习混乱，还可以增强对清晰图像的约束能力和无监督去雾的重建能力网络。此外，开发了自适应细粒度通道注意（FCA），利用相关矩阵来捕获不同粒度的全局和局部信息之间的相关性，促进它们之间的交互，实现更有效的特征权重分配。在具有挑战性的基准数据集上的实验结果证明了我们的 UBRFC-Net 相对于最先进的无监督图像去雾方法的优越性。这项研究成功地引入了一种增强的无监督图像去雾方法，解决了现有方法的局限性并取得了优异的去雾效果。源代码可在 处获得。