Deep Global Registration

Two indoor point-cloud scans move into alignment.

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.

Paper

paper

Oral Presentation

1-min Video

Quick Pipeline Video

Deep Global Registration, from two input scans to their final alignment.

Supplementary Materials

KITTI registration visualization

Two KITTI LiDAR scans move into registration.

Registration Results

All registration results of every 100th frames of the 3DMatch benchmark

Bibtex

@inproceedings{choy2020deep,
  title={Deep Global Registration},
  author={Choy, Christopher and Dong, Wei and Koltun, Vladlen},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2020}
}