LiDAR-enhanced 3D Gaussian Splatting Mapping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Jian, Yu, Huai, Wu, Ji, Yang, Wen, Xia, Gui-Song
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909530068090880
author Shen, Jian
Yu, Huai
Wu, Ji
Yang, Wen
Xia, Gui-Song
author_facet Shen, Jian
Yu, Huai
Wu, Ji
Yang, Wen
Xia, Gui-Song
contents This paper introduces LiGSM, a novel LiDAR-enhanced 3D Gaussian Splatting (3DGS) mapping framework that improves the accuracy and robustness of 3D scene mapping by integrating LiDAR data. LiGSM constructs joint loss from images and LiDAR point clouds to estimate the poses and optimize their extrinsic parameters, enabling dynamic adaptation to variations in sensor alignment. Furthermore, it leverages LiDAR point clouds to initialize 3DGS, providing a denser and more reliable starting points compared to sparse SfM points. In scene rendering, the framework augments standard image-based supervision with depth maps generated from LiDAR projections, ensuring an accurate scene representation in both geometry and photometry. Experiments on public and self-collected datasets demonstrate that LiGSM outperforms comparative methods in pose tracking and scene rendering.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05425
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LiDAR-enhanced 3D Gaussian Splatting Mapping
Shen, Jian
Yu, Huai
Wu, Ji
Yang, Wen
Xia, Gui-Song
Robotics
This paper introduces LiGSM, a novel LiDAR-enhanced 3D Gaussian Splatting (3DGS) mapping framework that improves the accuracy and robustness of 3D scene mapping by integrating LiDAR data. LiGSM constructs joint loss from images and LiDAR point clouds to estimate the poses and optimize their extrinsic parameters, enabling dynamic adaptation to variations in sensor alignment. Furthermore, it leverages LiDAR point clouds to initialize 3DGS, providing a denser and more reliable starting points compared to sparse SfM points. In scene rendering, the framework augments standard image-based supervision with depth maps generated from LiDAR projections, ensuring an accurate scene representation in both geometry and photometry. Experiments on public and self-collected datasets demonstrate that LiGSM outperforms comparative methods in pose tracking and scene rendering.
title LiDAR-enhanced 3D Gaussian Splatting Mapping
topic Robotics
url https://arxiv.org/abs/2503.05425