Spatial deformable transformer for 3D point cloud registration

Abstract Deformable attention only focuses on a small group of key sample-points around the reference point and make itself be able to capture dynamically the local features of input feature map without considering the size of the feature map. Its introduction into point cloud registration will be q...

Full description

Bibliographic Details
Main Authors: Fengguang Xiong, Yu Kong, Shuaikang Xie, Liqun Kuang, Xie Han
Format: Article
Language:English
Published: Nature Portfolio 2024-03-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-56217-9