# An approach to robust ICP initialization

arXiv: https://arxiv.org/abs/2212.05332 · HTML: https://mlsanity.com/paper/2212.05332/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 21 references that are in the map.
- First posted on arXiv 10 Dec 2022.

## Builds on (most cited first, 3 of 3)

- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [A comprehensive survey on point cloud registration](https://mlsanity.com/paper/2103.02690/) (2021)

## Built on by (most cited first, 2 of 2)

- [Robust affine point matching via quadratic assignment on Grassmannians](https://mlsanity.com/paper/2303.02698/) (2023)
- [Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context](https://mlsanity.com/paper/2509.24275/) (2025)

## Abstract (arXiv)

In this note, we propose an approach to initialize the Iterative Closest Point (ICP) algorithm to match unlabelled point clouds related by rigid transformations. The method is based on matching the ellipsoids defined by the points' covariance matrices and then testing the various principal half-axes matchings that differ by elements of a finite reflection group. We derive bounds on the robustness of our approach to noise and numerical experiments confirm our theoretical findings.