Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
This addresses the challenge of efficient and accurate multiview registration for 3D scanning applications, representing an incremental improvement over existing methods.
The paper tackles the problem of multiview point cloud registration by proposing a method that constructs a sparse, reliable pose graph using a neural network to estimate scan pair overlap and introduces a history reweighting function in IRLS for robustness to outliers. The result is an 11% higher registration recall on 3DMatch and ~13% lower errors on ScanNet while reducing pairwise registrations by ~70%.
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.