Correspondence-Free Multiview Point Cloud Registration via Depth-Guided Joint Optimisation

TL;DR

This paper presents a novel multiview point cloud registration method that uses depth maps and joint optimization to avoid explicit feature extraction and data association, improving accuracy in complex environments.

Contribution

It introduces a correspondence-free registration approach that jointly estimates poses and the global map using depth-guided non-linear optimization.

Findings

Outperforms state-of-the-art methods in accuracy

Effective in challenging environments with complex features

Implicit data association improves robustness

Abstract

Multiview point cloud registration is a fundamental task for constructing globally consistent 3D models. Existing approaches typically rely on feature extraction and data association across multiple point clouds; however, these processes are challenging to obtain global optimal solution in complex environments. In this paper, we introduce a novel correspondence-free multiview point cloud registration method. Specifically, we represent the global map as a depth map and leverage raw depth information to formulate a non-linear least squares optimisation that jointly estimates poses of point clouds and the global map. Unlike traditional feature-based bundle adjustment methods, which rely on explicit feature extraction and data association, our method bypasses these challenges by associating multi-frame point clouds with a global depth map through their corresponding poses. This data association is implicitly incorporated and dynamically refined during the optimisation process. Extensive evaluations on real-world datasets demonstrate that our method outperforms state-of-the-art approaches in accuracy, particularly in challenging environments where feature extraction and data association are difficult.