Vogiatzis George, Hernández Esteban Carlos, Torr Philip H S, Cipolla Roberto
Toshiba Research Europe Ltd., Cambridge, UK.
IEEE Trans Pattern Anal Mach Intell. 2007 Dec;29(12):2241-6. doi: 10.1109/TPAMI.2007.70712.
This paper presents a volumetric formulation for the multi-view stereo problem which is amenable to a computationally tractable global optimisation using Graph-cuts. Our approach is to seek the optimal partitioning of 3D space into two regions labelled as "object" and "empty" under a cost functional consisting of the following two terms: (1) A term that forces the boundary between the two regions to pass through photo-consistent locations and (2) a ballooning term that inflates the "object" region. To take account of the effect of occlusion on the first term we use an occlusion robust photo-consistency metric based on Normalised Cross Correlation, which does not assume any geometric knowledge about the reconstructed object. The globally optimal 3D partitioning can be obtained as the minimum cut solution of a weighted graph.
本文提出了一种用于多视图立体视觉问题的体积公式，该公式适用于使用图割进行计算上易于处理的全局优化。我们的方法是在一个由以下两个项组成的代价函数下，寻求将3D空间最优划分为标记为“物体”和“空”的两个区域：（1）一个迫使两个区域之间的边界通过照片一致位置的项；（2）一个使“物体”区域膨胀的膨胀项。为了考虑遮挡对第一项的影响，我们使用基于归一化互相关的遮挡鲁棒照片一致性度量，该度量不假设关于重建物体的任何几何知识。全局最优的3D划分可以作为加权图的最小割解获得。
