User: Guest  Login
Title:

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration

Document type:
Zeitschriftenaufsatz
Author(s):
Yu, Hao; Li, Fu; Saleh, Mahdi; Busam, Benjamin; Ilic, Slobodan
Abstract:
We study the problem of extracting correspondences between a pair of point clouds for registration. For correspondence retrieval, existing works benefit from matching sparse keypoints detected from dense points but usually struggle to guarantee their repeatability. To address this issue, we present CoFiNet - Coarse-to-Fine Network which extracts hierarchical correspondences from coarse to fine without keypoint detection. On a coarse scale and guided by a weighting scheme, our model firstly learn...     »
Journal title:
Advances in Neural Information Processing Systems
Year:
2021
Journal volume:
34
 BibTeX