We study the problem of outlier correspondence pruning for non-rigid point cloud registration. In rigid registration, spatial consistency has been a commonly used criterion to discriminate outliers from inliers. It measures the compatibility of two correspondences by the discrepancy between the respective distances in two point clouds. However, spatial consistency no longer holds in non-rigid cases and outlier rejection for non-rigid registration has not been well studied. In this work, we propose Graph-based Spatial Consistency Network (GraphSCNet) to filter outliers for non-rigid registration. Our method is based on the fact that non-rigid deformations are usually locally rigid, or local shape preserving. We first design a local spatial consistency measure over the deformation graph of the point cloud, which evaluates the spatial compatibility only between the correspondences in the vicinity of a graph node. An attention-based non-rigid correspondence embedding module is then devised to learn a robust representation of non-rigid correspondences from local spatial consistency. Despite its simplicity, GraphSCNet effectively improves the quality of the putative correspondences and attains state-of-the-art performance on three challenging benchmarks. Our code and models are available at https://github.com/qinzheng93/GraphSCNet.
翻译:我们研究非刚性点云配准中的异常对应消除问题。在刚性配准中,空间一致性通常用于区分异常和内点。它通过两个点云中对应点的距离差异来评估两个对应的兼容性。但是,空间一致性在非刚性情况下不再成立,非刚性配准的异常拒绝尚未得到充分研究。在本文中,我们提出了基于图形空间一致性的网络(GraphSCNet)来过滤非刚性配准的异常值。我们的方法基于非刚性变形通常具有本地刚性或本地形状保持的事实。我们首先设计了一种局部空间一致性度量,它在点云的变形图上仅评估相邻节点处对应的空间兼容性。然后,我们设计了一个基于注意力的非刚性对应嵌入模块,可以从局部空间一致性中学习到非刚性对应的稳健表示。尽管我们的方法非常简单,但GraphSCNet可以有效地提高候选对应的质量,并在三个具有挑战性的基准测试中达到了最先进的性能。我们的代码和模型可在https://github.com/qinzheng93/GraphSCNet上获得。