Single Image Haze Removal Using Dark Channel Prior（使用暗通道先验去除单张图像雾霾）

Abstract

In this paper, we propose a simple but effective image prior—dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of outdoor haze-free images. It is based on a key observation—most local patches in outdoor haze-free images contain some pixels whose intensity is very low in at least one color channel. Using this prior with the haze imaging model, we can directly estimate the thickness of the haze and recover a high quality haze-free image. Results on a variety of hazy images demonstrate the power of the proposed prior. Moreover, a high-quality depth map can also be obtained as a byproduct of haze removal.
在本文中，我们提出了一个简单但有效的图像先验-从单个输入图像中去除雾度之前的暗通道。 暗通道先验是一种户外无雾图像的统计数据。 它基于一项关键的观察-室外无雾图像中的大多数局部色块包含一些像素，这些像素在至少一个颜色通道中的强度非常低。 将其与雾度成像模型一起使用，我们可以直接估计雾度的厚度并恢复高质量的无雾图像。 在各种模糊图像上的结果证明了所提出的先验的力量。 此外，作为除雾的副产物，也可以获得高质量的深度图。

1.INTRODUCTION

IMAGES of outdoor scenes are usually degraded by the turbid medium (e.g., particles and water droplets) in the atmosphere. Haze, fog, and smoke are such phenomena due to atmospheric absorption and scattering.The irradiance received by the camera from the scene point is attenuated along the line of sight. Furthermore, the incoming light is blended with the airlight [1]—ambient light reflected into the line of sight by atmospheric particles. The degraded images lose contrast and color fidelity, as shown in Fig. 1a. Since the amount of scattering depends on the distance of the scene points from the camera, the degradation is spatially variant.
室外场景的图像通常会被大气中的浑浊介质（例如颗粒和水滴）降解。 雾，雾和烟雾是由于大气吸收和散射而产生的现象。相机从场景点接收到的辐照度沿视线衰减。 此外，入射光与空气[1]混合-反射到环境光中的环境光大气粒子的视线。 降级的图像失去对比度和色彩保真度，如图1a所示。 由于散射量取决于场景点与相机的距离，因此降级在空间上是变化的。
Haze removal 1 (or dehazing) is highly desired in consumer/computational photography and computer vision applications. First, removing haze can significantly increase the visibility of the scene and correct the color shift caused by the airlight. In general, the haze-free image is more visually pleasing. Second, most computer vision algorithms, from low-level image analysis to high-level object recognition, usually assume that the input image (after radiometric calibration) is the scene radiance. The performance of many vision algorithms (e.g., feature detection, filtering, and photometric analysis) will inevitably suffer from the biased and low-contrast scene radiance. Last, haze removal can provide depth information and benefit many vision algorithms and advanced image editing. Haze or fog can be a useful depth clue for scene understanding. A bad hazy image can be put to good use.
在消费者/计算摄影和计算机视觉应用中非常需要除雾1（或除雾）。 首先，消除雾气可以显着增加场景的可见度并纠正由光线引起的色偏。 通常，无雾图像在视觉上更令人愉悦。 其次，从低级图像分析到高级对象识别，大多数计算机视觉算法通常假定输入图像（辐射度校准后）是场景辐射度。 许多视觉算法（例如特征检测，滤波和光度分析）的性能将不可避免地受到偏光和低对比度场景辐射的影响。 最后，除雾可以提供深度信息，并有益于许多视觉算法和高级图像编辑。 雾或雾可能是了解场景的有用的深度线索。 不好的朦胧图像可以得到很好的利用。
However, haze removal is a challenging problem because the haze is dependent on the unknown depth.The problem is underconstrained if the input is only a single hazy image. Therefore, many methods have been proposed by using multiple images or additional information. Polarization- based methods [3], [4] remove the haze effect through two or more images taken with different degrees of polarization. In
[5], [6], [7], more constraints are obtained from multiple images of the same scene under different weather conditions. Depth-based methods [8], [9] require some depth information from user inputs or known 3D models.
但是，去除雾度是一个具有挑战性的问题，因为雾度取决于未知深度。如果输入仅是单个雾度图像，则该问题的约束不足。 因此，已经提出了通过使用多个图像或附加信息的许多方法。 基于偏振的方法[3]，[4]通过两个或多个以不同偏振度拍摄的图像消除了雾度效应。 在[5]，[6]，[7]，从不同天气条件下的同一场景的多个图像获得了更多的约束。 基于深度的方法[8]，[9]需要来自用户输入或已知3D模型的一些深度息。
Recently, single image haze removal has made significant progresses [10], [11]. The success of these methods lies on using stronger priors or assumptions. Tan [11] observes that a haze-free image must have higher contrast compared with the input hazy image and he removes haze by maximizing the local contrast of the restored image. The results are visually compelling but may not be physically valid. Fattal
[10] estimates the albedo of the scene and the medium transmission under the assumption that the transmission and the surface shading are locally uncorrelated. This approach is physically sound and can produce impressive results. However, it cannot handle heavily hazy images well and may fail in the cases where the assumption is broken.
近来，单图像雾度去除已取得了重大进展[10]，[11]。 这些方法的成功在于使用更强的先验或假设。 Tan [11]观察到，与输入模糊图像相比，无雾度图像必须具有更高的对比度，并且他通过使恢复图像的局部对比度最大化来消除雾度。 结果在视觉上令人信服，但在物理上可能无效。 致命的[10]在传输和表面阴影是局部不相关的假设下，估计了场景和介质传输的反照率。 这种方法在物理上是合理的，并且可以产生令人印象深刻的结果。 但是，它不能很好地处理非常模糊的图像，并且在假设被破坏的情况下可能会失败。
In this paper, we propose a novel prior—dark channel prior—for single image haze removal.The dark channel prior is based on the statistics of outdoor haze-free images.We find that, in most of the local regions which do not cover the sky, some pixels (called dark pixels) very often have very low intensity in at least one color (RGB) channel. In hazy images, the intensity of these dark pixels in that channel is mainly contributed by the airlight. Therefore, these dark pixels can directly provide an accurate estimation of the haze transmission. Combining a haze imaging model and a soft matting interpolation method, we can recover a high-quality haze-free image and produce a good depth map.
在本文中，我们提出了一种新颖的先验-暗通道先验-用于去除单个图像的雾度。暗通道先验是基于无畸变无图像的统计数据。我们发现，在大多数未覆盖的局部区域中 在天空中，某些像素（称为暗像素）通常在至少一种颜色（RGB）通道中的强度很低。 在模糊图像中，该通道中这些暗像素的强度主要是由飞机献。 因此，这些暗像素可以直接提供雾度透射率的准确估计。 结合雾度成像模型和软遮罩插值方法，我们可以恢复高质量的无雾度图像并生成良好的深度图。
Our approach is physically valid and is able to handledistant objects in heavily hazy images. We do not rely on significant variance of transmission or surface shading. The result contains few halo artifacts.
我们的方法在物理上是有效的，并且能够处理大量朦胧图像中的物体。 我们不依赖于透射率或表面阴影的显着变化。 结果包含很少的光晕伪像。

Like any approach using a strong assumption, our approach also has its own limitation. The dark channel prior may be invalid when the scene object is inherently similar to the airlight (e.g., snowy ground or a white wall) over a large local region and no shadow is cast on it. Although our approach works well for most outdoor hazy images, it may fail on some extreme cases. Fortunately, in such situations haze removal is not critical since haze is rarely visible. We believe that developing novel priors from different directions and combining them together will further advance the state of the art.
像使用强假设的任何方法一样，我们的方法也有其自身的局限性。 当场景对象在较大局部区域上本质上类似于空中照明（例如，雪地或白墙）且在其上没有阴影时，暗通道先验可能无效。 尽管我们的方法适用于大多数户外模糊图像，但在某些极端情况下可能会失败。 幸运的是，在这种情况下，去除雾霾并不重要，因为雾霾很少可见。 我们相信，从不同方向发展新颖的先验并将它们结合在一起将进一步提高技术水平。

2.BACKGROUND

在计算机视觉和计算机图形学中，广泛用于描述模糊图像形成的模型是[2]，[5]，[10]，[11]：

where I is the observed intensity, J is the scene radiance, A is the global atmospheric light, and t is the medium transmission describing the portion of the light that is not scattered and reaches the camera. The goal of haze removal is to recover J, A, and t from I. For an N-pixel color image I, there are 3N constraints and 4N +3 unknowns. This makes the problem of haze removal inherently ambiguous.
其中I是观测到的强度，J是场景辐射，A是全局大气光，t是介质传输，描述了未被散射并到达相机的那部分光。 去除雾度的目标是从I中恢复J，A和t。对于N像素彩色图像I，有3N个约束和4N +3个未知数。 这使得除雾问题固有地不明确。
In (1), the first term J（x）t(x) on the right-hand side is called direct attenuation [11], and the second term A(1-t(x)) is called airlight [1], [11]. The direct attenuation describes the scene radiance and its decay in the medium, and the airlight results from previously scattered light and leads to the shift of the scene colors. While the direct attenuation is a multiplicative distortion of the scene radiance, the airlight is an additive one.
在（1）中，将右边的第一项J（x）t（x）称为直接衰减[11]，将第二项A（1-t（x））称为airlight [1]， [11]。 直接衰减描述了场景的辐射度及其在介质中的衰减，而空中光线是由先前散射的光产生的，并导致场景颜色的偏移。 虽然直接衰减是场景辐射度的倍增失真，但导光灯是附加的。
When the atmosphere is homogenous, the transmission t can be expressed as
当大气均匀时，透射率t可以表示为

where β is the scattering coefficient of the atmosphere and d is the scene depth. This equation indicates that the scene radiance is attenuated exponentially with the depth. If we can recover the transmission, we can also recover the depth up to an unknown scale.
其中，β是大气的散射系数，d是场景深度。 该方程表明场景辐射度随深度呈指数衰减。 如果我们可以恢复传输，我们也可以恢复到未知的深度。
Geometrically, the haze imaging equation (1) means that in RGB color space, the vectors A, I(x) and J(x) are coplanar and their end points are collinear (see Fig. 2a). The transmission t is the ratio of two line segments:
在几何上，雾度成像方程式（1）表示在RGB颜色空间中，向量A，I（x）和J（x）是共面的，并且它们的端点是共线的（参见图2a）。 透射率t是两个线段的比率：

where c∈{r,g,b} is the color channel index.
其中c∈{r，g，b}是颜色通道索引。
Based on this model, T