MDCS with fully encoding the information of local shape description for 3D Rigid Data matching

作者：

Highlights：

• The mechanism relies on the integration of multi-view and multi-attribute strategy.

• MDCS achieves high descriptiveness and strong robustness to clutter and occlusion.

• MDCS is capable of high applicability on public datasets and the real-world point clouds.

摘要

•The mechanism relies on the integration of multi-view and multi-attribute strategy.•MDCS achieves high descriptiveness and strong robustness to clutter and occlusion.•MDCS is capable of high applicability on public datasets and the real-world point clouds.

论文关键词：Local feature description,3D rigid data matching,Multi-view,Local reference frame (LRF)

论文评审过程：Received 17 November 2021, Revised 12 February 2022, Accepted 17 February 2022, Available online 19 February 2022, Version of Record 18 March 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104421