Graph Matching Optimization Network for Point Cloud Registration

TL;DR

This paper introduces GMONet, a novel graph-matching optimization network that explicitly enforces isometry-preserving constraints during point feature training to enhance 3D point cloud registration accuracy.

Contribution

GMONet uniquely incorporates explicit isometry-preserving constraints into feature training using graph-matching optimization, improving registration performance.

Findings

Performs competitively on 3DMatch/3DLoMatch benchmarks.

Effective in optimizing point features with isometry constraints.

Accelerates optimization with inexact proximal point and mini-batch techniques.

Abstract

Point Cloud Registration is a fundamental and challenging problem in 3D computer vision. Recent works often utilize the geometric structure information in point feature embedding or outlier rejection for registration while neglecting to consider explicitly isometry-preserving constraint ($e.g.,$ point pair linked edge's length preserving after transformation) in training. We claim that the explicit isometry-preserving constraint is also important for improving feature representation abilities in the feature training stage. To this end, we propose a \underline{G}raph \underline{M}atching \underline{O}ptimization based \underline{Net}work (GMONet for short), which utilizes the graph-matching optimizer to explicitly exert the isometry preserving constraints in the point feature training to improve the point feature representation. Specifically, we exploit a partial graph-matching optimizer to optimize the super point ($i.e.,$ down-sampled key points) features and a full graph-matching optimizer to optimize fine-level point features in the overlap region. Meanwhile, we leverage the inexact proximal point method and the mini-batch sampling technique to accelerate these two graph-matching optimizers. Given high discriminative point features in the evaluation stage, we utilize the RANSAC approach to estimate the transformation between the scanned pairs. The proposed method has been evaluated on the 3DMatch/3DLoMatch benchmarks and the KITTI benchmark. The experimental results show that our method performs competitively compared to state-of-the-art baselines.