Rotation invariant point cloud analysis: Where local geometry meets global topology

作者：

Highlights：

• We present LGR-Net which considers local geometric features and global topology-preserving features to achieve rotation invariance.

• The complementary relationship between shape descriptions and spatial attributes is adaptively exploited by an attention-based fusion module.

• LGR-Net significantly outperforms state-of-the-art methods on both synthetic and real-world datasets undergoing random 3D rotations.

摘要

•We present LGR-Net which considers local geometric features and global topology-preserving features to achieve rotation invariance.•The complementary relationship between shape descriptions and spatial attributes is adaptively exploited by an attention-based fusion module.•LGR-Net significantly outperforms state-of-the-art methods on both synthetic and real-world datasets undergoing random 3D rotations.

论文关键词：Point cloud analysis,Rotation invariance,Deep learning,Classification,Segmentation

论文评审过程：Received 28 October 2020, Revised 21 February 2022, Accepted 5 March 2022, Available online 6 March 2022, Version of Record 19 March 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108626