Deep Global Registration

CVPR 2020

Deep Global Registration

Sep 29, 2020
|
28 views
|
|
Code
Details
Authors: Christopher Choy, Wei Dong, Vladlen Koltun Description: 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.

Comments
loading...