In this article, we study two less-touched challenging problems in single image dehazing neural networks, namely, how to remove haze from a given image in an unsupervised and zero-shot manner. To the ends, we propose a novel method based on the idea of layer disentanglement by viewing a hazy image as the entanglement of several “simpler” layers, i.e. , a hazy-free image layer, transmission map layer, and atmospheric light layer. The major advantages of the proposed ZID are two-fold. First, it is an unsupervised method that does not use any clean images including hazy-clean pairs as the ground-truth. Second, ZID is a “zero-shot” method, which just uses the observed single hazy image to perform learning and inference. In other words, it does not follow the conventional paradigm of training deep model on a large scale dataset. These two advantages enable our method to avoid the labor-intensive data collection and the domain shift issue of using the synthetic hazy images to address the real-world images. Extensive comparisons show the promising performance of our method compared with 15 approaches in the qualitative and quantitive evaluations. The source code could be found at http://www.pengxi.me .

中文翻译：

---

零镜头图像去雾。


在本文中，我们研究了单图像去雾神经网络中两个较少涉及的挑战性问题，即如何以无监督和零样本的方式从给定图像中去除雾霾。最后，我们提出了一种基于层解纠缠思想的新颖方法，将模糊图像视为几个“更简单”层的纠缠， IE 、无雾图像层、透射图层和大气光层。所提出的 ZID 的主要优点有两个。首先，它是一种无监督方法，不使用任何干净图像（包括模糊干净对）作为基本事实。其次，ZID是一种“零样本”方法，仅使用观察到的单个模糊图像来进行学习和推理。换句话说，它不遵循在大规模数据集上训练深度模型的传统范式。这两个优点使我们的方法能够避免劳动密集型数据收集和使用合成模糊图像来处理真实世界图像的域转移问题。广泛的比较表明，与 15 种方法相比，我们的方法在定性和定量评估方面具有良好的性能。源代码可以在以下位置找到http://www.pengxi.me 。