A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration

TL;DR

This paper introduces an unsupervised 3D point cloud registration method that separates pose-invariant and pose-related representations, improving robustness to partial and noisy data while achieving competitive results.

Contribution

It proposes a novel representation separation approach for correspondences-free registration, enhancing robustness and accuracy over existing methods.

Findings

Achieves comparable or better performance than supervised methods.

Robust to partial and noisy point clouds.

Effectively filters out pose-invariant disturbances.

Abstract

3D point cloud registration in remote sensing field has been greatly advanced by deep learning based methods, where the rigid transformation is either directly regressed from the two point clouds (correspondences-free approaches) or computed from the learned correspondences (correspondences-based approaches). Existing correspondences-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds. In this paper, we propose a correspondences-free unsupervised point cloud registration (UPCR) method from the representation separation perspective. First, we model the input point cloud as a combination of pose-invariant representation and pose-related representation. Second, the pose-related representation is used to learn the relative pose wrt a "latent canonical shape" for the source and target point clouds respectively. Third, the rigid transformation is obtained from the above two learned relative poses. Our method not only filters out the disturbance in pose-invariant representation but also is robust to partial-to-partial point clouds or noise. Experiments on benchmark datasets demonstrate that our unsupervised method achieves comparable if not better performance than state-of-the-art supervised registration methods.