A Strong Baseline for Point Cloud Registration via Direct Superpoints Matching

TL;DR

This paper introduces a simple, end-to-end trainable baseline for point cloud registration that matches superpoints globally using normalized scores, avoiding RANSAC and prediction errors, and achieves competitive results.

Contribution

The paper proposes a novel global matching approach for superpoints in point cloud registration that eliminates RANSAC and improves accuracy through end-to-end training.

Findings

Achieves comparable or better results than state-of-the-art methods.

Eliminates the need for RANSAC in registration.

Demonstrates effectiveness across multiple datasets.

Abstract

Deep neural networks endow the downsampled superpoints with highly discriminative feature representations. Previous dominant point cloud registration approaches match these feature representations as the first step, e.g., using the Sinkhorn algorithm. A RANSAC-like method is then usually adopted as a post-processing refinement to filter the outliers. Other dominant method is to directly predict the superpoint matchings using learned MLP layers. Both of them have drawbacks: RANSAC-based methods are computationally intensive and prediction-based methods suffer from outputing non-existing points in the point cloud. In this paper, we propose a straightforward and effective baseline to find correspondences of superpoints in a global matching manner. We employ the normalized matching scores as weights for each correspondence, allowing us to reject the outliers and further weigh the rest inliers when fitting the transformation matrix without relying on the cumbersome RANSAC. Moreover, the entire model can be trained in an end-to-end fashion, leading to better accuracy. Our simple yet effective baseline shows comparable or even better results than state-of-the-art methods on three datasets including ModelNet, 3DMatch, and KITTI. We do not advocate our approach to be \emph{the} solution for point cloud registration but use the results to emphasize the role of matching strategy for point cloud registration. The code and models are available at https://github.com/neu-vi/Superpoints_Registration.