Practical, Fast and Robust Point Cloud Registration for 3D Scene Stitching and Object Localization

TL;DR

This paper introduces VOCRA, a fast and robust method for 3D point cloud registration capable of handling over 99% outliers, improving accuracy and efficiency in scene stitching and object localization.

Contribution

The paper proposes a novel robust registration algorithm using Tukey's Biweight cost, efficient consensus maximization, and Graduated Non-Convexity, outperforming existing methods in robustness and speed.

Findings

VOCRA handles over 99% outliers effectively.

It is faster and more robust than current state-of-the-art methods.

Validated on benchmark and real-world datasets.

Abstract

3D point cloud registration ranks among the most fundamental problems in remote sensing, photogrammetry, robotics and geometric computer vision. Due to the limited accuracy of 3D feature matching techniques, outliers may exist, sometimes even in very large numbers, among the correspondences. Since existing robust solvers may encounter high computational cost or restricted robustness, we propose a novel, fast and highly robust solution, named VOCRA (VOting with Cost function and Rotating Averaging), for the point cloud registration problem with extreme outlier rates. Our first contribution is to employ the Tukey's Biweight robust cost to introduce a new voting and correspondence sorting technique, which proves to be rather effective in distinguishing true inliers from outliers even with extreme (99%) outlier rates. Our second contribution consists in designing a time-efficient consensus maximization paradigm based on robust rotation averaging, serving to seek inlier candidates among the correspondences. Finally, we apply Graduated Non-Convexity with Tukey's Biweight (GNC-TB) to estimate the correct transformation with the inlier candidates obtained, which is then used to find the complete inlier set. Both standard benchmarking and realistic experiments with application to two real-data problems are conducted, and we show that our solver VOCRA is robust against over 99% outliers and more time-efficient than the state-of-the-art competitors.