具有兼容性功能的3D通信插件
3D Correspondence Grouping with Compatibility Features
摘要：
我们提出了一个简单而有效的方法，三维对应分组。我们的目标是准确地分类的初始对应关系，通过匹配局部几何描述符到内点和离群点。虽然对应的空间分布是不规则的，但期望内点在几何上彼此相容。基于这样的观察，我们提出了一种新的表示为3D对应，称为兼容性功能（CF），来描述内点和离群点内的不一致。CF由候选项与其他对应项的排名最高的兼容性分数组成，这纯粹依赖于鲁棒性和旋转不变的几何约束。然后，我们制定的分组问题的CF功能，这是通过一个简单的多层感知器（MLP）网络的分类问题。在四个基准上与九种最先进的方法进行比较，结果表明：1）CF是独特的，鲁棒的，旋转不变的; 2）我们的基于CF的方法实现了最佳的整体性能，并具有良好的泛化能力。
英文摘要：
We present a simple yet effective method for 3D correspondence grouping. The objective is to accurately classify initial correspondences obtained by matching local geometric descriptors into inliers and outliers. Although the spatial distribution of correspondences is irregular, inliers are expected to be geometrically compatible with each other. Based on such observation, we propose a novel representation for 3D correspondences, dubbed compatibility feature (CF), to describe the consistencies within inliers and inconsistencies within outliers. CF consists of top-ranked compatibility scores of a candidate to other correspondences, which purely relies on robust and rotation-invariant geometric constraints. We then formulate the grouping problem as a classification problem for CF features, which is accomplished via a simple multilayer perceptron (MLP) network. Comparisons with nine state-of-the-art methods on four benchmarks demonstrate that: 1) CF is distinctive, robust, and rotation-invariant; 2) our CF-based method achieves the best overall performance and holds good generalization ability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
