SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences

TL;DR

This paper introduces SDRSAC, a robust point cloud registration method that uses semidefinite relaxation and randomized sampling to handle noisy data without relying on correspondences, outperforming existing techniques.

Contribution

It presents a novel semidefinite relaxation-based randomized approach enabling point cloud registration without correspondences, improving robustness and efficiency.

Findings

Outperforms state-of-the-art registration methods.

Effectively rejects outliers in noisy data.

Provides a generic framework extendable to known correspondence problems.

Abstract

This paper presents a novel randomized algorithm for robust point cloud registration without correspondences. Most existing registration approaches require a set of putative correspondences obtained by extracting invariant descriptors. However, such descriptors could become unreliable in noisy and contaminated settings. In these settings, methods that directly handle input point sets are preferable. Without correspondences, however, conventional randomized techniques require a very large number of samples in order to reach satisfactory solutions. In this paper, we propose a novel approach to address this problem. In particular, our work enables the use of randomized methods for point cloud registration without the need of putative correspondences. By considering point cloud alignment as a special instance of graph matching and employing an efficient semi-definite relaxation, we propose a novel sampling mechanism, in which the size of the sampled subsets can be larger-than-minimal. Our tight relaxation scheme enables fast rejection of the outliers in the sampled sets, resulting in high-quality hypotheses. We conduct extensive experiments to demonstrate that our approach outperforms other state-of-the-art methods. Importantly, our proposed method serves as a generic framework which can be extended to problems with known correspondences.