Deep Global Registration

Christopher Choy; Wei Dong; Vladlen Koltun

CVPR 2020oral621 citations

Deep Global Registration

Christopher Choy, Wei Dong, Vladlen Koltun

Abstract

We present Deep Global Registration, a differentiable framework for pairwise registration of real-world 3D scans. Deep global registration is based on three modules: a 6-dimensional convolutional network for correspondence confidence prediction, a differentiable Weighted Procrustes algorithm for closed-form pose estimation, and a robust gradient-based SE(3) optimizer for pose refinement. Experiments demonstrate that our approach outperforms state-of-the-art methods, both learning-based and classical, on real-world data.

BibTeX

@inproceedings{cvpr2020_deepglobalregist,
  title = {Deep Global Registration},
  author = {Christopher Choy and Wei Dong and Vladlen Koltun},
  booktitle = {CVPR 2020},
  year = {2020}
}