BO-ICP: Initialization of Iterative Closest Point Based on Bayesian Optimization

TL;DR

This paper introduces BO-ICP, a Bayesian optimization-based method for selecting initial transforms in ICP point cloud registration, improving accuracy and efficiency over existing stochastic and global optimization approaches.

Contribution

The paper presents a novel Bayesian optimization approach for initializing ICP, demonstrating versatility and superior performance compared to state-of-the-art methods.

Findings

Outperforms existing methods with similar computation time

Versatile configurations for rapid and refined results

Compatible with other ICP improvements

Abstract

Typical algorithms for point cloud registration such as Iterative Closest Point (ICP) require a favorable initial transform estimate between two point clouds in order to perform a successful registration. State-of-the-art methods for choosing this starting condition rely on stochastic sampling or global optimization techniques such as branch and bound. In this work, we present a new method based on Bayesian optimization for finding the critical initial ICP transform. We provide three different configurations for our method which highlights the versatility of the algorithm to both find rapid results and refine them in situations where more runtime is available such as offline map building. Experiments are run on popular data sets and we show that our approach outperforms state-of-the-art methods when given similar computation time. Furthermore, it is compatible with other improvements to ICP, as it focuses solely on the selection of an initial transform, a starting point for all ICP-based methods.