GraphMatch: Efficient Large-Scale Graph Construction for Structure from Motion
GraphMatch: Efficient Large-Scale Graph Construction for Structure from Motion
复制标题
DOI：
10.1109/3dv.2017.00028
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
Qiaodong Cui;Victor Fragoso;Chris Sweeney;P. Sen
中科院分区：
文献类型：
--
作者：
Qiaodong Cui;Victor Fragoso;Chris Sweeney;P. Sen
本文提出了一种近似而有效的从运动恢复结构（Structure-from-Motion~（SfM））管道匹配图的构造方法GraphMatch。GraphMatch利用两个先验知识，可以预测哪些图像对可能匹配，从而使SfM的匹配过程更加高效。第一个是从任何两个图像的Fisher向量之间的距离计算的分数。第二个先验是基于底层匹配图中顶点之间的图距离。GraphMatch将这两个先验结合到一个迭代的“采样和传播”方案中，类似于PatchMatch算法。它的采样阶段使用Fisher相似性先验来指导匹配图像对的搜索，而它的传播阶段则探索匹配图像对的邻居，以找到具有高图像相似性得分的新图像。我们的实验表明，GraphMatch找到最多的图像对相比，竞争，近似的方法，而在同一时间是最有效的。
We present GraphMatch, an approximate yet efficient method for building the matching graph for large-scale structure-from-motion~(SfM) pipelines. GraphMatch leverages two priors that can predict which image pairs are likely to match, thereby making the matching process for SfM much more efficient. The first is a score computed from the distance between the Fisher vectors of any two images. The second prior is based on the graph distance between vertices in the underlying matching graph. GraphMatch combines these two priors into an iterative ``sample-and-propagate'' scheme similar to the PatchMatch algorithm. Its sampling stage uses Fisher similarity priors to guide the search for matching image pairs, while its propagation stage explores neighbors of matched pairs to find new ones with a high image similarity score. Our experiments show that GraphMatch finds the most image pairs as compared to competing, approximate methods while at the same time being the most efficient.