# GraffMatch: Global Matching of 3D Lines and Planes for Wide Baseline LiDAR Registration

arXiv: https://arxiv.org/abs/2212.12745 · HTML: https://mlsanity.com/paper/2212.12745/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 24 Dec 2022.

## Builds on (most cited first, 17 of 17)

- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments](https://mlsanity.com/paper/2109.13494/) (2021)
- [SegMatch: Segment based loop-closure for 3D point clouds](https://mlsanity.com/paper/1609.07720/) (2016)
- [ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants](https://mlsanity.com/paper/2011.03659/) (2020)
- [CLIPPER: A Graph-Theoretic Framework for Robust Data Association](https://mlsanity.com/paper/2011.10202/) (2020)
- [Automatic Extrinsic Calibration Method for LiDAR and Camera Sensor Setups](https://mlsanity.com/paper/2101.04431/) (2021)
- [Gaussians on Riemannian Manifolds: Applications for Robot Learning and Adaptive Control](https://mlsanity.com/paper/1909.05946/) (2019)
- [Observability Analysis of Aided INS with Heterogeneous Features of Points, Lines and Planes](https://mlsanity.com/paper/1805.05876/) (2018)
- [Long-Term Urban Vehicle Localization Using Pole Landmarks Extracted from 3-D Lidar Scans](https://mlsanity.com/paper/1910.10550/) (2019)
- [Online Range Image-based Pole Extractor for Long-term LiDAR Localization in Urban Environments](https://mlsanity.com/paper/2108.08621/) (2021)
- [Global Data Association for SLAM with 3D Grassmannian Manifold Objects](https://mlsanity.com/paper/2205.08556/) (2022)
- [Object Tracking via Non-Euclidean Geometry: A Grassmann Approach](https://mlsanity.com/paper/1403.0309/) (2014)
- [Advanced Situational Graphs for Robot Navigation in Structured Indoor Environments](https://mlsanity.com/paper/2211.08754/) (2022)

## Built on by (most cited first, 3 of 3)

- [G3Reg: Pyramid Graph-based Global Registration using Gaussian Ellipsoid Model](https://mlsanity.com/paper/2308.11573/) (2023)
- [CLIPPER+: A Fast Maximal Clique Algorithm for Robust Global Registration](https://mlsanity.com/paper/2402.15464/) (2024)
- [CLIPPER: Robust Data Association without an Initial Guess](https://mlsanity.com/paper/2402.07284/) (2024)

## Abstract (arXiv)

Using geometric landmarks like lines and planes can increase navigation accuracy and decrease map storage requirements compared to commonly-used LiDAR point cloud maps. However, landmark-based registration for applications like loop closure detection is challenging because a reliable initial guess is not available. Global landmark matching has been investigated in the literature, but these methods typically use ad hoc representations of 3D line and plane landmarks that are not invariant to large viewpoint changes, resulting in incorrect matches and high registration error. To address this issue, we adopt the affine Grassmannian manifold to represent 3D lines and planes and prove that the distance between two landmarks is invariant to rotation and translation if a shift operation is performed before applying the Grassmannian metric. This invariance property enables the use of our graph-based data association framework for identifying landmark matches that can subsequently be used for registration in the least-squares sense. Evaluated on a challenging landmark matching and registration task using publicly-available LiDAR datasets, our approach yields a 1.7x and 3.5x improvement in successful registrations compared to methods that use viewpoint-dependent centroid and "closest point" representations, respectively.