arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.02583cs.CV
收藏

基于典型重叠点的点云配准

Point Cloud Registration using Representative Overlapping Points

DeepGlint(深瞐科技);Shanghai Jiao Tong University(上海交通大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)

Lifa Zhu, Dongrui Liu, Changwei Lin, Rui Yan, Francisco Gómez-Fernández, Ninghua Yang, Ziyong Feng

摘要:

三维点云配准是机器人学和计算机视觉中的一项基本任务。近年来,出现了许多基于学习的点云配准方法。然而,这些方法严重依赖于这样的对应关系,并遇到了很大的挑战与部分重叠。在本文中,我们提出了ROPNet,这是一种新的深度学习模型,使用具有区分特征的代表性重叠点进行配准,将部分到部分配准转换为部分到完整配准。具体来说,我们提出了一个上下文引导模块,它使用编码器来提取全局特征,用于预测点重叠分数。为了更好地找到有代表性的重叠点,我们使用提取的全局特征进行粗对齐。然后,我们引入了一个Transformer来丰富点的特征,并删除非代表点的基础上点重叠得分和特征匹配。采用部分到完全的方式建立相似度矩阵,最后采用加权奇异值分解估计变换矩阵。在ModelNet40上使用噪声和部分重叠的点云进行的大量实验表明,所提出的方法优于传统的基于学习的方法,实现了最先进的性能。该代码可在https://github.com/zhulf0804/ROPNet上获得。

英文摘要:

3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such correspondences and meet great challenges with partial overlap. In this paper, we propose ROPNet, a new deep learning model using Representative Overlapping Points with discriminative features for registration that transforms partial-to-partial registration into partial-to-complete registration. Specifically, we propose a context-guided module which uses an encoder to extract global features for predicting point overlap score. To better find representative overlapping points, we use the extracted global features for coarse alignment. Then, we introduce a Transformer to enrich point features and remove non-representative points based on point overlap score and feature matching. A similarity matrix is built in a partial-to-complete mode, and finally, weighted SVD is adopted to estimate a transformation matrix. Extensive experiments over ModelNet40 using noisy and partially overlapping point clouds show that the proposed method outperforms traditional and learning-based methods, achieving state-of-the-art performance. The code is available at https://github.com/zhulf0804/ROPNet.

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。

↑