Deep Global Registration

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 stateof-the-art methods, both learning-based and classical, on real-world data.

Paper

paper

Oral Presentation

1-min Video

Quick Pipeline Video

Supplementary Materials

• Supplementary paper
• Code
• Poster

• KITTI registration visualizataion

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}
}