SANDRO: a Robust Solver with a Splitting Strategy for Point Cloud Registration
This addresses a critical issue for navigation systems in robotics and computer vision, offering a robust solution for handling high outlier rates and skewed distributions, though it appears incremental as it builds on existing IRLS frameworks.
The paper tackles the problem of point cloud registration in computer vision and robotics, where existing methods struggle with high outlier rates and slow convergence, by introducing SANDRO, a novel algorithm that achieves a 20% improvement in success rate on real data and 60% on synthetic data compared to state-of-the-art methods.
Point cloud registration is a critical problem in computer vision and robotics, especially in the field of navigation. Current methods often fail when faced with high outlier rates or take a long time to converge to a suitable solution. In this work, we introduce a novel algorithm for point cloud registration called SANDRO (Splitting strategy for point cloud Alignment using Non-convex anD Robust Optimization), which combines an Iteratively Reweighted Least Squares (IRLS) framework with a robust loss function with graduated non-convexity. This approach is further enhanced by a splitting strategy designed to handle high outlier rates and skewed distributions of outliers. SANDRO is capable of addressing important limitations of existing methods, as in challenging scenarios where the presence of high outlier rates and point cloud symmetries significantly hinder convergence. SANDRO achieves superior performance in terms of success rate when compared to the state-of-the-art methods, demonstrating a 20% improvement from the current state of the art when tested on the Redwood real dataset and 60% improvement when tested on synthetic data.