Semantic enhancement based adaptive geometric encoding network for low overlap point cloud registration

Abstract

The presence of partial or low overlaps in real point cloud pairs poses significant challenges to obtain robust registration. There is an absence of a unified framework that localizes reliable overlapping regions and correspondences. This work proposes an adaptive point cloud geometric encoding network based on semantic enhancement that generates overlap information with geometric-and-semantic consistency in various scenarios. This enables the network to further ensure distinctive geometric representation when the low overlap point cloud pairs have scarce differences in the geometric structures. In addition, our study includes experiments conducted on a self-created semantic-assisted dataset designed to facilitate in-depth research on point cloud registration. The experimental results clearly demonstrate the efficacy and overall improvements of the registration performance, particularly highlighting the potential of our approach in addressing the challenges associated with low overlap scenarios that have repetitive geometry patterns.