Recent unsupervised image dehazing methods used unpaired real-world training data for enhancing generalization on real-world scenes. However, these methods often require dehazing and rehazing cycles with auxiliary networks for training, resulting in high computational costs and extended training time. In this work, we propose an unsupervised dehazing framework called Contrastive Adaptive Frequency Decomposition Dehazing Network (CAFDD). By incorporating carefully designed network structure and constraints, our CAFDD well avoids additional training overhead and needs only 1.91M parameters. Specifically, we first consider the following insights, including: (1) Haze primarily affects high-frequency components in an image, resulting in blurred edges; (2) Low-frequency components capture the large-scale variations with less susceptibility to haze; and (3) Existing unlearnable frequency decomposition methods such Fourier transform often suffer from information loss, and thus develop the novel PMP (Pointwise convolution-Max pooling-Pointwise convolution) and DAD (Depthwise convolution-Average pooling-Depthwise convolution) blocks to automatically extract high and low-frequency features from input images for accurately estimating transmission map. Then, we propose haze discrimination (HD), a new pretext task for contrastive learning in image dehazing, by forming positive and negative pairs based on haze presence, in order for guiding the network to extract visibility-related features. Last, to get rid of the rehazing cycle and improve training efficiency, we construct a pixel-level constraint, histogram equalization-based texture loss function, which enhances the sharpness and realism of the generated images. Through extensive experiments, we demonstrate the superiority of our CAFDD over the state-of-the-art dehazing approaches on real-world land and overwater images.

中文翻译：

---

由雾度辨别引导的对比自适应频率分解网络用于现实世界图像去雾

最近的无监督图像去雾方法使用不成对的现实世界训练数据来增强对现实世界场景的泛化。然而，这些方法通常需要使用辅助网络进行去雾和再雾化循环进行训练，从而导致计算成本较高和训练时间延长。在这项工作中，我们提出了一种无监督的去雾框架，称为对比自适应频率分解去雾网络（CAFDD）。通过结合精心设计的网络结构和约束，我们的 CAFDD 很好地避免了额外的训练开销，并且只需要 1.91M 参数。具体来说，我们首先考虑以下见解，包括：（1）雾度主要影响图像中的高频成分，导致边缘模糊； (2) 低频分量捕捉大范围变化，不易受雾霾影响； （3）现有的不可学习的频率分解方法（例如傅立叶变换）经常会遭受信息丢失，因此开发了新颖的PMP（Pointwise CNN-Max pooling-Pointwise CNN）和DAD（Depthwise CNN-Average pooling-Depthwise CNN）块来自动提取输入图像的高频和低频特征，用于准确估计传输图。然后，我们提出了雾霾辨别（HD），这是一种用于图像去雾对比学习的新借口任务，通过基于雾霾的存在形成正负对，以指导网络提取与可见性相关的特征。最后，为了摆脱重新雾化循环并提高训练效率，我们构建了像素级约束、基于直方图均衡的纹理损失函数，增强了生成图像的清晰度和真实感。通过大量实验，我们证明了 CAFDD 相对于现实世界陆地和水上图像最先进的去雾方法的优越性。