Single image dehazing is the ill-posed two-dimensional signal reconstruction problem. Recently, deep convolutional neural networks (CNN) have been successfully used in many computer vision problems. In this paper, we propose a Y-net that is named for its structure. This network reconstructs clear images by aggregating multi-scale features maps. Additionally, we propose a Wavelet Structure SIMilarity (W-SSIM) loss function in the training step. In the proposed loss function, discrete wavelet transforms are applied repeatedly to divide the image into differently sized patches with different frequencies and scales. The proposed loss function is the accumulation of SSIM loss of various patches with respective ratios. Extensive experimental results demonstrate that the proposed Y-net with the W-SSIM loss function restores high-quality clear images and outperforms state-of-the-art algorithms. Code and models are available at https://github.com/dectrfov/Y-net.

中文翻译：

---

Y-net：用于单幅图像去雾的具有小波结构相似性损失函数的多尺度特征聚合网络

单幅图像去雾是不适定的二维信号重建问题。最近，深度卷积神经网络 (CNN) 已成功应用于许多计算机视觉问题。在本文中，我们提出了一个以其结构命名的 Y-net。该网络通过聚合多尺度特征图重建清晰的图像。此外，我们在训练步骤中提出了小波结构相似性 (W-SSIM) 损失函数。在提出的损失函数中，离散小波变换被重复应用以将图像划分为具有不同频率和尺度的不同大小的块。建议的损失函数是具有各自比率的各种补丁的 SSIM 损失的累积。大量的实验结果表明，所提出的带有 W-SSIM 损失函数的 Y-net 可以恢复高质量的清晰图像并优于最先进的算法。代码和模型可从 https://github.com/dectrfov/Y-net 获得。