A Direct Semi-Exhaustive Search Method for Robust, Partial-to-Full Point Cloud Registration

TL;DR

This paper introduces DSES, a GPU-accelerated semi-exhaustive search algorithm for robust point cloud registration that directly optimizes transformations without correspondences, outperforming existing methods in accuracy and robustness.

Contribution

The paper presents a novel semi-exhaustive search approach for point cloud registration that operates without correspondences and leverages GPU parallelism for improved performance.

Findings

Outperforms state-of-the-art registration methods on ModelNet40 benchmark.

Demonstrates high robustness and accuracy in real-world robotics pose estimation.

Efficiently computes transformations using parallelized semi-exhaustive search.

Abstract

Point cloud registration refers to the problem of finding the rigid transformation that aligns two given point clouds, and is crucial for many applications in robotics and computer vision. The main insight of this paper is that we can directly optimize the point cloud registration problem without correspondences by utilizing an algorithmically simple, yet computationally complex, semi-exhaustive search approach that is very well-suited for parallelization on modern GPUs. Our proposed algorithm, Direct Semi-Exhaustive Search (DSES), iterates over potential rotation matrices and efficiently computes the inlier-maximizing translation associated with each rotation. It then computes the optimal rigid transformation based on any desired distance metric by directly computing the error associated with each transformation candidate $\{R, t\}$. By leveraging the parallelism of modern GPUs, DSES outperforms state-of-the-art methods for partial-to-full point cloud registration on the simulated ModelNet40 benchmark and demonstrates high performance and robustness for pose estimation on a real-world robotics problem (https://youtu.be/q0q2-s2KSuA).