Shape, Illumination, and Reflectance from Shading
Shape, Illumination, and Reflectance from Shading
复制标题
DOI：
10.1109/tpami.2014.2377712
复制
发表时间：
2015-08-01
影响因子：
23.6
通讯作者：
Malik, Jitendra
中科院分区：
文献类型：
--
作者：
Barron, Jonathan T.;Malik, Jitendra
计算机视觉中的一个基本问题是从该世界的平坦的2D图像推断世界的内在3D结构。恢复场景属性（例如形状，反射率或照明）的传统方法依赖于对同一场景的多个观察来避免问题。相比之下，从单个图像中恢复了相同的属性似乎几乎是不可能的 - 有无限数量的形状，油漆和灯，这些形状，油漆和灯光完全重现了单个图像。但是，某些解释比其他解释更有可能：表面往往是光滑的，油漆往往是均匀的，并且照明往往是自然的。因此，我们将这个问题作为统计推断之一，并定义一个优化问题，该问题搜索最可能的单个图像解释。我们的技术可以看作是几个经典的计算机视觉问题的超集（形状从阴影，固有图像，颜色恒定，照明估算等），并且对这些组成问题的所有以前的解决方案都超过了所有解决方案。
A fundamental problem in computer vision is that of inferring the intrinsic, 3D structure of the world from flat, 2D images of that world. Traditional methods for recovering scene properties such as shape, reflectance, or illumination rely on multiple observations of the same scene to overconstrain the problem. Recovering these same properties from a single image seems almost impossible in comparison-there are an infinite number of shapes, paint, and lights that exactly reproduce a single image. However, certain explanations are more likely than others: surfaces tend to be smooth, paint tends to be uniform, and illumination tends to be natural. We therefore pose this problem as one of statistical inference, and define an optimization problem that searches for the most likely explanation of a single image. Our technique can be viewed as a superset of several classic computer vision problems (shape-from-shading, intrinsic images, color constancy, illumination estimation, etc) and outperforms all previous solutions to those constituent problems.