DeepBBS: Deep Best Buddies for Point Cloud Registration
release_jdvwtve3lvhphmyiji3z5sd5bq
by
Itan Hezroni, Amnon Drory, Raja Giryes, Shai Avidan
2021
Abstract
Recently, several deep learning approaches have been proposed for point cloud
registration. These methods train a network to generate a representation that
helps finding matching points in two 3D point clouds. Finding good matches
allows them to calculate the transformation between the point clouds
accurately. Two challenges of these techniques are dealing with occlusions and
generalizing to objects of classes unseen during training. This work proposes
DeepBBS, a novel method for learning a representation that takes into account
the best buddy distance between points during training. Best Buddies (i.e.,
mutual nearest neighbors) are pairs of points nearest to each other. The Best
Buddies criterion is a strong indication for correct matches that, in turn,
leads to accurate registration. Our experiments show improved performance
compared to previous methods. In particular, our learned representation leads
to an accurate registration for partial shapes and in unseen categories.
In text/plain
format
Archived Files and Locations
application/pdf 5.6 MB
file_hzfojou5bbhmjl6hd7xqlh27q4
|
arxiv.org (repository) web.archive.org (webarchive) |
2110.03016v1
access all versions, variants, and formats of this works (eg, pre-prints)