Self-supervised rigid transformation equivariance for accurate 3D point cloud registration
Pattern Recognition(2022)
摘要
•We build a dedicated RTE and design a Siamese structurefor 3D point cloud registration.•We propose to learn the matching matrix from the LCV more effectively instead of the hand crafted matching strategy.•Remarkable performance on several datasets topping the state of the art methods proves the effectiveness of our method.
更多查看译文
关键词
Point cloud,Rigid transformation equivariance,Learned cost volume
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要