Point Clouds Registration is a fundamental and challenging problem in 3D computer vision. It has been shown that the isometric transformation is an essential property in rigid point cloud registration, but the existing methods only utilize it in the outlier rejection stage. In this paper, we emphasize that the isometric transformation is also important in the feature learning stage for improving registration quality. We propose a \underline{G}raph \underline{M}atching \underline{O}ptimization based \underline{Net}work (denoted as GMONet for short), which utilizes the graph matching method to explicitly exert the isometry preserving constraints in the point feature learning stage to improve %refine the point representation. Specifically, we %use exploit the partial graph matching constraint to enhance the overlap region detection abilities of super points ($i.e.,$ down-sampled key points) and full graph matching to refine the registration accuracy at the fine-level overlap region. Meanwhile, we leverage the mini-batch sampling to improve the efficiency of the full graph matching optimization. Given high discriminative point features in the evaluation stage, we utilize the RANSAC approach to estimate the transformation between the scanned pairs. The proposed method has been evaluated on the 3DMatch/3DLoMatch benchmarks and the KITTI benchmark. The experimental results show that our method achieves competitive performance compared with the existing state-of-the-art baselines.

翻译：点云配准是三维计算机视觉中一个基础且具有挑战性的问题。已有研究表明，等距变换是刚性点云配准中的一个关键属性，但现有方法仅在外点剔除阶段利用该属性。本文强调，等距变换在特征学习阶段对于提升配准质量同样重要。为此，我们提出了一种基于图匹配优化网络（简称GMONet），该方法利用图匹配技术在点特征学习阶段显式施加等距保持约束，以改进点表征。具体而言，我们利用部分图匹配约束增强超点（即下采样关键点）的重叠区域检测能力，并通过全图匹配优化精细级重叠区域的配准精度。同时，我们采用小批量采样提高全图匹配优化的效率。在评估阶段，基于高判别性点特征，我们使用RANSAC方法估计扫描对之间的变换矩阵。所提方法已在3DMatch/3DLoMatch基准和KITTI基准上进行了评估。实验结果表明，与现有最先进基线方法相比，我们的方法取得了具有竞争力的性能。