Feature matching aims at generating correspondences across images, which is widely used in many computer vision tasks. Although considerable progress has been made on feature descriptors and fast matching for initial correspondence hypotheses, selecting good ones from them is still challenging and critical to the overall performance. More importantly, existing methods often take a long computational time, limiting their use in real-time applications. This paper attempts to separate true correspondences from false ones at high speed. We term the proposed method (GMS) grid-based motion Statistics, which incorporates the smoothness constraint into a statistic framework for separation and uses a grid-based implementation for fast calculation. GMS is robust to various challenging image changes, involving in viewpoint, scale, and rotation. It is also fast, e.g., take only 1 or 2 ms in a single CPU thread, even when 50 K correspondences are processed. This has important implications for real-time applications. What’s more, we show that incorporating GMS into the classic feature matching and epipolar geometry estimation pipeline can significantly boost the overall performance. Finally, we integrate GMS into the well-known ORB-SLAM system for monocular initialization, resulting in a significant improvement.

中文翻译：

---

GMS：基于网格的运动统计，用于快速、超稳健的特征对应

特征匹配旨在生成图像之间的对应关系，广泛用于许多计算机视觉任务。尽管在特征描述符和初始对应假设的快速匹配方面取得了相当大的进展，但从中选择好的假设仍然具有挑战性，并且对整体性能至关重要。更重要的是，现有方法通常需要很长的计算时间，限制了它们在实时应用中的使用。本文试图高速分离真实的对应关系和虚假的对应关系。我们将提议的方法（GMS）称为基于网格的运动统计，该方法将平滑约束合并到用于分离的统计框架中，并使用基于网格的实现进行快速计算。GMS 对各种具有挑战性的图像变化具有鲁棒性，包括视点、比例和旋转。它也很快，例如，在单个 CPU 线程中仅需要 1 或 2 毫秒，即使处理 50 K 对应。这对实时应用程序具有重要意义。此外，我们表明将 GMS 纳入经典特征匹配和对极几何估计管道可以显着提高整体性能。最后，我们将 GMS 集成到著名的 ORB-SLAM 系统中进行单目初始化，取得了显着的改进。