Inevitable hazy contamination degrades the visibility of images, and the resulting haze removal is one of the essential prerequisites for image processing and computer vision tasks. We proposed an end-to-end dehazing network, referred to as Guided-Pix2Pix, to estimate spatially refined transmission maps and dehaze via the physical scattering equation. The remaining enhancement of color contrast, ill-posed adversarial training, and redundant backbone, however, should be thoroughly investigated, as required in the prospect of Guided-Pix2Pix. In this paper, we inherit the end-to-end structure of Guided-Pix2Pix and accordingly propose Guided-Pix2Pix+ as an update, which concatenates transmission estimation and refinement, physical scattering equation-based dehazing, together with color refinement, to achieve haze removal in a one-stage way. Specifically, we make use of the pretrained instance of EfficientNetB0 to estimate coarse-grained transmission maps and concatenate a guided filter layer to perform spatial refinement for the incoming transmission maps. Restored by the physical scattering equation, color refinement of dehazed proposals is finally performed via the standardization and clipping of pixel intensities. All the operations are differentiable, making it possible to achieve end-to-end, tight training. Furthermore, adversarial and perceptual losses are employed to regulate the performance of our model, giving rise to structurally similar but photo-realistic dehazed proposals. Extensive experiments confirm that our Guided-Pix2Pix+ yields dehazed proposals with fine-grained spatial refinement and relatively effective color contrast, compared to our previous Guided-Pix2Pix, the baseline, and advanced dehazing methods. The source code is currently available at https://github.com/92xianshen/guided-pix2pixplus.

不可避免的雾霾污染会降低图像的可见性，由此产生的雾霾去除是图像处理和计算机视觉任务的基本先决条件之一。我们提出了一个端到端的去雾网络，称为 Guided-Pix2Pix，通过物理散射方程估计空间精细的透射图和去雾。然而，根据 Guided-Pix2Pix 的前景，应该彻底研究颜色对比度、不适定对抗训练和冗余骨干的剩余增强。在本文中，我们继承了Guided-Pix2Pix的端到端结构，并据此提出了Guided-Pix2Pix+作为更新，它将透射估计和细化、基于物理散射方程的去雾与颜色细化相结合，以一步方式实现去雾。具体来说，我们利用 EfficientNetB0 的预训练实例来估计粗粒度传输图，并连接一个引导滤波器层以对传入的传输图执行空间细化。通过物理散射方程恢复，去雾提议的颜色细化最终通过像素强度的标准化和裁剪来执行。所有的操作都是可区分的，从而可以实现端到端的紧密训练。此外，对抗性和感知损失被用来调节我们模型的性能，从而产生结构相似但逼真的去雾提议。大量实验证实，与我们之前的 Guided-Pix2Pix、基线和高级去雾方法相比，我们的 Guided-Pix2Pix+ 产生具有细粒度空间细化和相对有效的颜色对比度的去雾提议。源代码目前可在 https://github.com/92xianshen/guided-pix2pixplus 获得。