IEEE Trans Pattern Anal Mach Intell. 2015 Aug;37(8):1670-87. doi: 10.1109/TPAMI.2014.2377712.
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.
计算机视觉中的一个基本问题是如何从世界的二维平面图像推断出其内在的三维结构。传统的方法，如形状、反射率或光照的场景属性恢复，依赖于对同一场景的多次观察来过度约束问题。相比之下，从单个图像中恢复这些相同的属性似乎几乎不可能——有无数种形状、油漆和灯光可以完全复制单个图像。然而，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，照明往往是自然的。因此，我们将这个问题作为一个统计推断问题来解决，并定义了一个优化问题，该问题搜索单个图像最可能的解释。我们的技术可以被视为几个经典计算机视觉问题（从阴影中恢复形状、内在图像、颜色恒常性、光照估计等）的超集，并且优于这些组成问题的所有先前解决方案。
