We present a new approach for selecting image pairs that are more likely to match in Structure from Motion (SfM). We propose to use Jaccard Similarity (JacS) which shows how many different visual words is shared by an image pair. In our method, the similarity between images is evaluated using JacS of bag-of-visual-words in addition to tf-idf (term frequency-inverse document frequency), which is popular for this purpose. To evaluate the efficiency of our method, we carry out experiments on our original datasets as well as on “Pantheon” dataset, which is derived from Flickr. The result of our method using both JacS and tf-idf is better than the results of a standard method using tf-idf only.

中文翻译：

---

通过引入Jaccard相似度为SfM选择图像对

我们提出了一种从运动（SfM）中选择更有可能在结构上匹配的图像对的新方法。我们建议使用Jaccard相似度（JacS），它显示图像对共享多少个不同的视觉单词。在我们的方法中，除了tf-idf（术语频率-反向文档频率）外，还使用视觉单词袋的JacS评估图像之间的相似性，这在此目的上很普遍。为了评估我们方法的效率，我们对原始数据集以及源自Flickr的“万神殿”数据集进行了实验。我们同时使用JacS和tf-idf的方法的结果要好于仅使用tf-idf的标准方法的结果。