Can generalised relative pose estimation solve sparse 3D registration?

TL;DR

This paper introduces a novel approach for sparse 3D scan registration that leverages line intersection constraints and plane correspondences, outperforming existing methods on Kinect and LiDAR datasets.

Contribution

It proposes a new formulation using line segments and plane constraints, along with minimal solvers and an alternating projection algorithm for improved sparse 3D registration.

Findings

Outperforms competing methods on Kinect datasets

Effective in sparse 3D registration without RGB data

Introduces minimal solvers for line and plane constraints

Abstract

Popular 3D scan registration projects, such as Stanford digital Michelangelo or KinectFusion, exploit the high-resolution sensor data for scan alignment. It is particularly challenging to solve the registration of sparse 3D scans in the absence of RGB components. In this case, we can not establish point correspondences since the same 3D point cannot be captured in two successive scans. In contrast to correspondence based methods, we take a different viewpoint and formulate the sparse 3D registration problem based on the constraints from the intersection of line segments from adjacent scans. We obtain the line segments by modeling every horizontal and vertical scan-line as piece-wise linear segments. We propose a new alternating projection algorithm for solving the scan alignment problem using line intersection constraints. We develop two new minimal solvers for scan alignment in the presence of plane correspondences: 1) 3 line intersections and 1 plane correspondence, and 2) 1 line intersection and 2 plane correspondences. We outperform other competing methods on Kinect and LiDAR datasets.