Deep Global Registration

CVPR 2020  ·  Christopher Choy, Wei Dong, Vladlen Koltun ·

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.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Datasets

KITTI 3DMatch
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Point Cloud Registration 3DLoMatch (10-30% overlap) DGR (reported in REGTR) Recall ( correspondence RMSE below 0.2) 48.7 # 7
Compare
Point Cloud Registration 3DMatch (at least 30% overlapped - FCGF setting) DGR (RE (all), TE(all) are reported in PCAM) Recall (0.3m, 15 degrees) 91.3 # 4
Compare
RE (all) 9.5 # 3
Compare
TE (all) 0.25 # 4
Compare
Point Cloud Registration 3DMatch (at least 30% overlapped - sample 5k interest points) DGR (reported in REGTR) Recall ( correspondence RMSE below 0.2) 85.3 # 6
Compare
Point Cloud Registration KITTI (FCGF setting) DGR + ICP (RE (all), TE(all) are reported in PCAM) Recall (0.6m, 5 degrees) 98.2 # 2
Compare
RE (all) 1.43 # 5
Compare
TE (all) 0.16 # 2
Compare
Point Cloud Registration KITTI (FCGF setting) DGR (RE (all), TE(all) are reported in PCAM) Recall (0.6m, 5 degrees) 96.9 # 7
Compare
RE (all) 1.62 # 6
Compare
TE (all) 0.34 # 6
Compare

Methods
Add Remove

Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy