Interactive ( De ) Weathering of an Image using Physical Models ∗
Interactive ( De ) Weathering of an Image using Physical Models ∗
复制标题
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
S. Narasimhan;S. Nayar
中科院分区：
文献类型：
--
作者：
S. Narasimhan;S. Nayar
在恶劣天气下拍摄的场景图像的对比度和色彩较差。众所周知，恶劣天气导致的图像质量下降在场景点的深度呈指数级下降。因此，从场景的单个图像恢复场景颜色和对比度本质上是受到限制的。最近，研究表明，在不同天气条件下拍摄的同一场景的多幅图像或通过不同成像光学器件拍摄的多幅图像可以用来打破除风化过程中的模糊性。在本文中，我们解决了使用用户交互提供的简单附加信息对单个图像进行去风化的问题。我们利用先前工作中描述的基于物理的模型，并开发了三种交互式算法，以从单个图像中消除天气影响，并向单个图像添加天气影响。我们使用在恶劣天气条件下拍摄的几张图像展示了有效的色彩和对比度恢复。此外，我们还展示了向图像添加天气效果的示例。我们的图像（去）风化交互式方法可以作为各种图像处理软件的易于使用的插件。 1 交互式去风化的需求 在雾、薄雾、雨和雪等恶劣天气条件下拍摄的图像对比度较差，色彩严重损坏。在恶劣天气下，场景点的辐射由于大气散射而显着改变。散射量取决于场景点与观察者的距离。因此，从恶劣天气下拍摄的单张图像中恢复晴天的场景对比度和颜色本质上受到限制。最近，视觉和图像处理领域对恶劣天气下的色彩和对比度恢复进行了大量研究。当已知准确的场景深度 [6, 8] 以及有关大气条件的精确信息 [1] 时，可以对图像进行去风化。在计算机视觉中，已经开发出算法来计算场景结构并自动恢复场景对比度和颜色，而不需要任何有关大气或场景深度的信息。这些算法通过使用多个来打破除风化中存在的模糊性 *这项工作得到了 DARPA HumanID 合同 (N000-14-00-1-0916) 和 NSF 奖 (IIS-99-87979) 的支持。在不同天气条件下拍摄的同一场景的图像 [3, 4] 或通过改变成像光学器件获取的多个图像 [7]。在这项工作中，我们解决了如何在不使用精确天气或深度信息的情况下对场景的单个图像进行去风化的问题。回想一下，之前的工作表明，同一场景的多个图像对于打破去风化中的模糊性是必要的。然而，在许多情况下，可能无法获取多个图像。例如，如今，有数百万张由业余和专业摄影师拍摄的照片因天气而损坏，几乎没有标记有关深度或大气的信息。很多时候，我们可能拥有的只是一张我们希望去除风化的场景的照片。在这种情况下，我们将证明，使用用户的最少额外输入可以成功地打破图像去风化过程中的歧义。我们首先回顾两个散射模型 [3, 4]，它们描述了恶劣天气条件下场景的颜色和对比度。基于这些模型，我们提出了三种算法来交互式地对单个图像进行去风化。在所有这些情况下，用户通过可视界面向我们基于物理的算法提供简单的输入，以恢复场景的对比度和颜色。输入的类型（例如，场景深度增加的大致方向，或粗略的深度分割或良好颜色保真度的区域）可能因场景而异，但很容易为人类用户提供。我们还使用类似的交互方法向图像添加基于物理的天气效果。我们展示了一些结果，说明了在恶劣天气条件下捕获的彩色和灰度图像的有效去风化。我们的算法不需要有关场景结构或大气条件的精确信息，因此可以作为现有图像处理软件（例如 Adobe Photoshop）的易于使用的插件。我们相信，我们的交互式方法将使风化（去）化得到广泛应用。 2 恶劣天气下的颜色和对比度 在本节中，我们回顾了两个描述恶劣天气下场景点的颜色和对比度的单散射模型。这些模型在我们的交互式方法中用于去除天气并向图像添加天气。
Images of scenes acquired in bad weather have poor contrasts and colors. It is known that the degradation of image quality due to bad weather is exponential in the depths of the scene points. Therefore, restoring scene colors and contrasts from a single image of the scene is inherently under-constrained. Recently, it has been shown that multiple images of the same scene taken under different weather conditions or multiple images taken by varying imaging optics can be used to break the ambiguities in deweathering. In this paper, we address the question of deweathering a single image using simple additional information provided interactively by the user. We exploit the physics-based models described in prior work and develop three interactive algorithms to remove weather effects from, and add weather effects to, a single image. We demonstrate effective color and contrast restoration using several images taken under poor weather conditions. Furthermore, we show an example of adding weather effects to images. Our interactive methods for image (de)weathering can serve as easy-touse plug-ins for a variety of image processing software. 1 Need for Interactive Deweathering Images taken under bad weather conditions such as fog, mist, rain and snow suffer from poor contrasts and severely corrupted colors. In bad weather, the radiance from a scene point is significantly altered due to atmospheric scattering. The amount of scattering depends on the distances of scene points from the observer. Therefore, restoring clear day contrasts and colors of a scene from a single image taken in bad weather is inherently under-constrained. Recently, there has been considerable research in the vision and image processing communities on color and contrast restoration in bad weather. Deweathering an image has been demonstrated when accurate scene depths are known [6, 8] and when precise information about the atmospheric condition is known [1]. In computer vision, algorithms have been developed to compute scene structure and restore scene contrasts and colors automatically without requiring any information about the atmosphere or scene depths. These algorithms break the ambiguities that exist in deweathering by using multiple ∗This work was supported by a DARPA HumanID Contract (N000-14-00-1-0916) and an NSF Award (IIS-99-87979). images of the same scene taken under different weather conditions [3, 4] or multiple images acquired by varying the imaging optics [7]. In this work, we address the question of how to deweather a single image of a scene without using precise weather or depth information. Recall that previous work showed that multiple images of the same scene are necessary to break the ambiguities in deweathering. However, in many cases, it may not be possible to acquire multiple images. For instance, today, there are millions of pictures corrupted by weather, that are taken by amateur and professional photographers, with virtually no information about the depths or the atmosphere tagged to them. Very often, all we may have is a single photograph of a scene that we wish to deweather. In such cases, we will show that using minimal additional input from the user can successfully break the ambiguities in deweathering an image. We begin by reviewing two scattering models [3, 4] that describe the colors and contrasts of a scene under bad weather conditions. Based on these models, we then present three algorithms to interactively deweather a single image. In all these cases, the user provides simple inputs through a visual interface to our physics-based algorithms for restoring contrasts and colors of the scene. The types of input (for instance, approximate direction in which scene depths increase, or a rough depth segmentation or a region of good color fidelity) may vary from scene to scene, but are easy to provide for a human user. We also use similar interactive methods to add physically-based weather effects to images. We show several results that illustrate effective deweathering of both color and gray-scale images captured under harsh weather conditions. Our algorithms do not require precise information about scene structure or atmospheric condition and can thus serve as easy-to-use plug-ins for existing image processing software, such as Adobe Photoshop . We believe that our interactive methods will make (de)weathering widely applicable. 2 Colors and Contrasts in Bad Weather In this section, we review two single scattering models that describe colors and contrasts of scene points in bad weather. These models are used in our interactive methods to deweather, and add weather to images.