Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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.

Haiping Wang, Yuan Liu, Zhen Dong, Yulan Guo, Yu-Shen Liu, Wenping Wang, Bisheng Yang• 2023

Related benchmarks

TaskDatasetResultRank
Point cloud registration3DMatch (test)
Registration Recall96.2
393
3D Point Cloud Registration3DMatch
Translation Error (cm)11.6
44
Rigid Registration3DLoMatch (test)
RR83
43
Point cloud registrationETH--
38
Pose EstimationKITTI-360
RPE Translation (cm)95.576
29
Multiview RegistrationScanNet 30 scans 18
RE@3°59.4
19
Pose EstimationnuScenes
Translation Error (cm)30.383
17
Multiway point cloud registration3DLoMatch
Rotation Error (°)10.18
16
Multiway point cloud registrationKITTI
RE (°)4.69
16
Multi-view RegistrationScanNet (test)
Rotation Error (< 3°)57.2
15
Showing 10 of 13 rows

Other info

Code

Follow for update