论文标题
S2DNET：学习稀疏到密度匹配的准确对应关系
S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching
论文作者
论文摘要
建立强大而准确的对应关系是许多计算机视觉算法的基本骨干。尽管最近基于学习的功能匹配方法在具有挑战性的条件下提供了可靠的对应关系，但在精度方面通常受到限制。在本文中，我们介绍了S2DNET，这是一种新颖的功能匹配管道，设计和训练，以有效地建立强大和准确的对应关系。通过利用稀疏到密度的匹配范式，我们将对应学习问题作为监督分类任务，以学习输出高峰值的对应图。我们表明，S2DNET在HPATCHES基准以及几个长期视觉定位数据集上实现了最新的结果。
Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging conditions, they are often limited in terms of precision. In this paper, we introduce S2DNet, a novel feature matching pipeline, designed and trained to efficiently establish both robust and accurate correspondences. By leveraging a sparse-to-dense matching paradigm, we cast the correspondence learning problem as a supervised classification task to learn to output highly peaked correspondence maps. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.
