PCR-99: A Practical Method for Point Cloud Registration with 99 Percent Outliers
This addresses the problem of handling extreme outliers in point cloud registration for applications like robotics and computer vision, representing a strong specific gain rather than a foundational advancement.
The paper tackles robust point cloud registration with extreme outlier ratios, proposing PCR-99, which achieves comparable performance to state-of-the-art methods up to 98% outliers and outperforms them at 99% outliers, particularly in unknown-scale scenarios with improved robustness and speed.
We propose a robust method for point cloud registration that can handle both unknown scales and extreme outlier ratios. Our method, dubbed PCR-99, uses a deterministic 3-point sampling approach with two novel mechanisms that significantly boost the speed: (1) an improved ordering of the samples based on pairwise scale consistency, prioritizing the point correspondences that are more likely to be inliers, and (2) an efficient outlier rejection scheme based on triplet scale consistency, prescreening bad samples and reducing the number of hypotheses to be tested. Our evaluation shows that, up to 98% outlier ratio, the proposed method achieves comparable performance to the state of the art. At 99% outlier ratio, however, it outperforms the state of the art for both known-scale and unknown-scale problems. Especially for the latter, we observe a clear superiority in terms of robustness and speed.