arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00937cs.CV
收藏

OMNet:用于部分点云配准的学习重叠掩模

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

University of Electronic Science and Technology of China(电子科技大学);Megvii Technology(旷视科技)

Hao Xu, Shuaicheng Liu, Guangfu Wang, Guanghui Liu, Bing Zeng

摘要:

点云配准是许多计算领域中的一个关键问题。以前的对应匹配方法要求输入具有独特的几何结构,以适应一个3D刚性变换,根据逐点稀疏特征匹配。然而,转换的准确性在很大程度上依赖于提取的特征的质量,这是容易相对于噪声和噪声的错误。此外,它们不能利用所有重叠区域的几何知识。另一方面,以前的基于全局特征的方法可以利用整个点云进行配准,但是它们在聚合全局特征时忽略了非重叠点的负面影响。在本文中,我们提出了OMNet,一个基于全局特征的迭代网络,用于部分到部分点云配准。我们学习重叠掩模来拒绝非重叠区域,这将部分到部分配准转换为相同形状的配准。此外,以前使用的数据仅从每个对象的CAD模型中采样一次,从而为源和参考生成相同的点云。我们提出了一种更实用的数据生成方式,其中CAD模型被采样两次用于源和参考,避免了以前普遍存在的过拟合问题。实验结果表明,与传统方法和基于深度学习的方法相比,我们的方法达到了最先进的性能。代码可在https://github.com/megvii-research/OMNet上获得。

英文摘要:

Point cloud registration is a key task in many computational fields. Previous correspondence matching based methods require the inputs to have distinctive geometric structures to fit a 3D rigid transformation according to point-wise sparse feature matches. However, the accuracy of transformation heavily relies on the quality of extracted features, which are prone to errors with respect to partiality and noise. In addition, they can not utilize the geometric knowledge of all the overlapping regions. On the other hand, previous global feature based approaches can utilize the entire point cloud for the registration, however they ignore the negative effect of non-overlapping points when aggregating global features. In this paper, we present OMNet, a global feature based iterative network for partial-to-partial point cloud registration. We learn overlapping masks to reject non-overlapping regions, which converts the partial-to-partial registration to the registration of the same shape. Moreover, the previously used data is sampled only once from the CAD models for each object, resulting in the same point clouds for the source and reference. We propose a more practical manner of data generation where a CAD model is sampled twice for the source and reference, avoiding the previously prevalent over-fitting issue. Experimental results show that our method achieves state-of-the-art performance compared to traditional and deep learning based methods. Code is available at https://github.com/megvii-research/OMNet.

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。

↑