Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)

by   Kexue Fu, et al.

3D point cloud registration is a fundamental problem in computer vision and robotics. Recently, learning-based point cloud registration methods have made great progress. However, these methods are sensitive to outliers, which lead to more incorrect correspondences. In this paper, we propose a novel deep graph matching-based framework for point cloud registration. Specifically, we first transform point clouds into graphs and extract deep features for each point. Then, we develop a module based on deep graph matching to calculate a soft correspondence matrix. By using graph matching, not only the local geometry of each point but also its structure and topology in a larger range are considered in establishing correspondences, so that more correct correspondences are found. We train the network with a loss directly defined on the correspondences, and in the test stage the soft correspondences are transformed into hard one-to-one correspondences so that registration can be performed by a correspondence-based solver. Furthermore, we introduce a transformer-based method to generate edges for graph construction, which further improves the quality of the correspondences. Extensive experiments on object-level and scene-level benchmark datasets show that the proposed method achieves state-of-the-art performance. The code is available at: \href{}{}.


page 4

page 10


Robust Point Cloud Registration Framework Based on Deep Graph Matching

3D point cloud registration is a fundamental problem in computer vision ...

A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registration

Registration is a basic yet crucial task in point cloud processing. In c...

COTReg:Coupled Optimal Transport based Point Cloud Registration

Generating a set of high-quality correspondences or matches is one of th...

HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration

Point cloud registration is a fundamental problem in 3D computer vision....

HybridPoint: Point Cloud Registration Based on Hybrid Point Sampling and Matching

Patch-to-point matching has become a robust way of point cloud registrat...

DReg-NeRF: Deep Registration for Neural Radiance Fields

Although Neural Radiance Fields (NeRF) is popular in the computer vision...

REGTR: End-to-end Point Cloud Correspondences with Transformers

Despite recent success in incorporating learning into point cloud regist...

Please sign up or login with your details

Forgot password? Click here to reset