Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
About
In this paper, we present a new method for the multiview registration of point cloud. Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively Reweighted Least Square (IRLS) on the pose graph to compute the scan poses. However, constructing a densely-connected graph is time-consuming and contains lots of outlier edges, which makes the subsequent IRLS struggle to find correct poses. To address the above problems, we first propose to use a neural network to estimate the overlap between scan pairs, which enables us to construct a sparse but reliable pose graph. Then, we design a novel history reweighting function in the IRLS scheme, which has strong robustness to outlier edges on the graph. In comparison with existing multiview registration methods, our method achieves 11% higher registration recall on the 3DMatch dataset and ~13% lower registration errors on the ScanNet dataset while reducing ~70% required pairwise registrations. Comprehensive ablation studies are conducted to demonstrate the effectiveness of our designs.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Point cloud registration | 3DMatch (test) | Registration Recall96.2 | 339 | |
| Rigid Registration | 3DLoMatch (test) | RR83 | 43 | |
| Point cloud registration | ETH | -- | 38 | |
| 3D Point Cloud Registration | 3DMatch | Translation Error (cm)11.6 | 20 | |
| Multiview Registration | ScanNet 30 scans 18 | RE@3°59.4 | 19 | |
| Multiway point cloud registration | 3DLoMatch | Rotation Error (°)10.18 | 16 | |
| Multiway point cloud registration | KITTI | RE (°)4.69 | 16 | |
| Multi-view Registration | ScanNet (test) | Rotation Error (< 3°)57.2 | 15 | |
| Multiway point cloud registration | NSS | RE (Deg)10.87 | 8 | |
| Multiway point cloud registration | NSS | RR (%)66.9 | 8 |