COTReg:Coupled Optimal Transport based Point Cloud Registration

Abstract

Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration. This paper proposes a learning framework COTReg by jointly considering the pointwise and structural matchings to predict correspondences of 3D point cloud registration. Specifically, we transform the two matchings into a Wasserstein distance-based and a Gromov-Wasserstein distance-based optimizations, respectively. Thus the task of establishing the correspondences can be naturally reshaped to a coupled optimal transport problem. Furthermore, we design a network to predict the confidence score of being an inlier for each point of the point clouds, which provides the overlap region information to generate correspondences. Our correspondence prediction pipeline can be easily integrated into either learning-based features like FCGF or traditional descriptors like FPFH. We conducted comprehensive experiments on 3DMatch, KITTI, 3DCSR, and ModelNet40 benchmarks, showing the state-of-art performance of the proposed method.

Hierarchical Optimization of 3D Point Cloud Registration

“…Inspired by [10], [11], [24], [25], we propose Graph Matching Optimization based Network (GMONet for short) to explicitly incorporate the graph matching constraint to learn the "rigid" geometric features. We utilize KPConv [16] as our feature backbone network and deploy graph-matching optimizers to enhance the isometry-preserving feature representation in training.…”