Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration

TL;DR

This paper introduces GraphSCNet, a novel graph-based neural network that leverages local spatial consistency to effectively filter outliers in non-rigid point cloud registration, significantly improving registration accuracy.

Contribution

It proposes a local spatial consistency measure and an attention-based embedding module for robust non-rigid correspondence filtering, advancing outlier rejection methods.

Findings

Achieves state-of-the-art results on three benchmarks.

Effectively filters outliers in non-rigid registration.

Improves registration accuracy significantly.

Abstract

We study the problem of outlier correspondence pruning for non-rigid point cloud registration. In rigid registration, spatial consistency has been a commonly used criterion to discriminate outliers from inliers. It measures the compatibility of two correspondences by the discrepancy between the respective distances in two point clouds. However, spatial consistency no longer holds in non-rigid cases and outlier rejection for non-rigid registration has not been well studied. In this work, we propose Graph-based Spatial Consistency Network (GraphSCNet) to filter outliers for non-rigid registration. Our method is based on the fact that non-rigid deformations are usually locally rigid, or local shape preserving. We first design a local spatial consistency measure over the deformation graph of the point cloud, which evaluates the spatial compatibility only between the correspondences in the vicinity of a graph node. An attention-based non-rigid correspondence embedding module is then devised to learn a robust representation of non-rigid correspondences from local spatial consistency. Despite its simplicity, GraphSCNet effectively improves the quality of the putative correspondences and attains state-of-the-art performance on three challenging benchmarks. Our code and models are available at https://github.com/qinzheng93/GraphSCNet.