arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.09154cs.CV
收藏

CMG-Net:基于Chamfer法线距离与多尺度几何的点云鲁棒法线估计

CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-scale Geometry

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(中国科学院香港创新研究院);SenseTime Research(商汤科技研究院);Soochow University(苏州大学)

Yingrui Wu, Mingyang Zhao, Keqiang Li, Weize Quan, Tianqi Yu, Jianfeng Yang, Xiaohong Jia, Dong-Ming Yan

AI总结:

针对点云法线估计中方向不一致与尺度选择模糊问题,提出基于Chamfer法线距离和多尺度几何架构的CMG-Net,在合成与真实数据集尤其是含噪场景下达到SOTA性能。

摘要:

本研究提出了一种精确且鲁棒的点云法线估计方法。现有方法直接最小化标注法线与预测法线间的偏差,易导致方向不一致问题,对此我们首先提出名为Chamfer Normal Distance(Chamfer法线距离)的新指标来解决该问题。该指标不仅缓解了这一挑战,还能促进网络训练,大幅提升网络抗噪声鲁棒性。随后,我们设计了一种创新架构,包含Multi-scale Local Feature Aggregation(多尺度局部特征聚合)与Hierarchical Geometric Information Fusion(分层几何信息融合),使网络能更有效地捕捉复杂几何细节,缓解尺度选择的模糊性。大量实验表明,我们的方法在合成数据集与真实数据集上均达到了SOTA(当前最优)性能,在受噪声污染的场景中表现尤为突出。代码已开源至https://github.com/YingruiWoo/CMG-Net_Pytorch。

英文摘要:

This work presents an accurate and robust method for estimating normals from point clouds. In contrast to predecessor approaches that minimize the deviations between the annotated and the predicted normals directly, leading to direction inconsistency, we first propose a new metric termed Chamfer Normal Distance to address this issue. This not only mitigates the challenge but also facilitates network training and substantially enhances the network robustness against noise. Subsequently, we devise an innovative architecture that encompasses Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion. This design empowers the network to capture intricate geometric details more effectively and alleviate the ambiguity in scale selection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on both synthetic and real-world datasets, particularly in scenarios contaminated by noise. Our implementation is available at https://github.com/YingruiWoo/CMG-Net_Pytorch.

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。

↑