Deep Global Registration
2020-04-24CVPR 2020Code Available1· sign in to hype
Christopher Choy, Wei Dong, Vladlen Koltun
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/chrischoy/DeepGlobalRegistrationOfficialIn paperpytorch★ 543
- github.com/chrischoy/FCGFpytorch★ 721
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 3DLoMatch (10-30% overlap) | DGR (reported in REGTR) | Recall ( correspondence RMSE below 0.2) | 48.7 | — | Unverified |
| 3DMatch (at least 30% overlapped - FCGF setting) | DGR (RE (all), TE(all) are reported in PCAM) | Recall (0.3m, 15 degrees) | 91.3 | — | Unverified |
| 3DMatch (at least 30% overlapped - sample 5k interest points) | DGR (reported in REGTR) | Recall ( correspondence RMSE below 0.2) | 85.3 | — | Unverified |
| KITTI (FCGF setting) | DGR + ICP (RE (all), TE(all) are reported in PCAM) | Recall (0.6m, 5 degrees) | 98.2 | — | Unverified |
| KITTI (FCGF setting) | DGR (RE (all), TE(all) are reported in PCAM) | Recall (0.6m, 5 degrees) | 96.9 | — | Unverified |