Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Giacomini, Emanuele, Di Giammarino, Luca, De Rebotti, Lorenzo, Grisetti, Giorgio, Oswald, Martin R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912286926438400
author Giacomini, Emanuele
Di Giammarino, Luca
De Rebotti, Lorenzo
Grisetti, Giorgio
Oswald, Martin R.
author_facet Giacomini, Emanuele
Di Giammarino, Luca
De Rebotti, Lorenzo
Grisetti, Giorgio
Oswald, Martin R.
contents LiDARs provide accurate geometric measurements, making them valuable for ego-motion estimation and reconstruction tasks. Although its success, managing an accurate and lightweight representation of the environment still poses challenges. Both classic and NeRF-based solutions have to trade off accuracy over memory and processing times. In this work, we build on recent advancements in Gaussian Splatting methods to develop a novel LiDAR odometry and mapping pipeline that exclusively relies on Gaussian primitives for its scene representation. Leveraging spherical projection, we drive the refinement of the primitives uniquely from LiDAR measurements. Experiments show that our approach matches the current registration performance, while achieving SOTA results for mapping tasks with minimal GPU requirements. This efficiency makes it a strong candidate for further exploration and potential adoption in real-time robotics estimation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17491
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping
Giacomini, Emanuele
Di Giammarino, Luca
De Rebotti, Lorenzo
Grisetti, Giorgio
Oswald, Martin R.
Robotics
Computer Vision and Pattern Recognition
LiDARs provide accurate geometric measurements, making them valuable for ego-motion estimation and reconstruction tasks. Although its success, managing an accurate and lightweight representation of the environment still poses challenges. Both classic and NeRF-based solutions have to trade off accuracy over memory and processing times. In this work, we build on recent advancements in Gaussian Splatting methods to develop a novel LiDAR odometry and mapping pipeline that exclusively relies on Gaussian primitives for its scene representation. Leveraging spherical projection, we drive the refinement of the primitives uniquely from LiDAR measurements. Experiments show that our approach matches the current registration performance, while achieving SOTA results for mapping tasks with minimal GPU requirements. This efficiency makes it a strong candidate for further exploration and potential adoption in real-time robotics estimation tasks.
title Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.17491