Single Image Dehazing Using Haze-Lines
Single Image Dehazing Using Haze-Lines
复制标题
DOI：
10.1109/tpami.2018.2882478
复制
发表时间：
2020-03-01
影响因子：
23.6
通讯作者：
Avidan, Shai
中科院分区：
文献类型：
--
作者：
Berman, Dana;Treibitz, Tali;Avidan, Shai
雾霾通常会限制能见度，降低户外图像的对比度。由于物体与相机的距离不同，图像的退化在空间上是不同的。这种依赖关系用传输系数表示，传输系数控制衰减。从单个图像中恢复场景亮度是一个高度病态的问题，因此需要使用图像先验。与使用基于补丁的图像先验的方法相反，我们提出了一种基于非局部先验的算法。该算法依赖于一个假设，即无雾图像的颜色由几百种不同的颜色很好地近似，这些颜色在RGB空间中形成紧密的簇。我们的关键观察是，给定集群中的像素通常是非局部的，即分布在整个图像平面上，并且位于与相机的不同距离上。在有雾霾的情况下，这些不同的距离转化为不同的透射系数。因此，清晰图像中的每个颜色簇都成为RGB空间中的一条线，我们称之为模糊线。利用这些雾线，我们的算法恢复了大气光、距离图和无雾图像。该算法具有线性复杂性，不需要训练，并且与其他最先进的方法相比，在各种各样的图像上表现良好。
Haze often limits visibility and reduces contrast in outdoor images. The degradation varies spatially since it depends on the objects' distances from the camera. This dependency is expressed in the transmission coefficients, which control the attenuation. Restoring the scene radiance from a single image is a highly ill-posed problem, and thus requires using an image prior. Contrary to methods that use patch-based image priors, we propose an algorithm based on a non-local prior. The algorithm relies on the assumption that colors of a haze-free image are well approximated by a few hundred distinct colors, which form tight clusters in RGB space. Our key observation is that pixels in a given cluster are often non-local, i.e., spread over the entire image plane and located at different distances from the camera. In the presence of haze these varying distances translate to different transmission coefficients. Therefore, each color cluster in the clear image becomes a line in RGB space, that we term a haze-line. Using these haze-lines, our algorithm recovers the atmospheric light, the distance map and the haze-free image. The algorithm has linear complexity, requires no training, and performs well on a wide variety of images compared to other state-of-the-art methods.