Range-View-Based Normal Estimation for Sparse LiDAR SLAM.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

View graph of relations

Details

Original languageEnglish
Title of host publication2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN)
EditorsJari Nurmi, Simona Lohan, Aleksandr Ometov, Lucie Klus, Christopher Mutschler, Joaquin Torres-Sospedra
Pages1-6
Number of pages6
ISBN (electronic)979-8-3315-5680-8
Publication statusPublished - 15 Sept 2025

Abstract

Accurate surface normal estimation is critical for LiDAR-based tasks such as mapping, localization, and scene understanding. However, traditional 3D neighborhood selection methods often struggle with sparse point clouds due to uneven density and sensor limitations. In this paper, we propose a geometry-aware approach that leverages the structured 2D range view to select more consistent neighborhoods for normal estimation. By combining adaptive windowing in range space with distance-based filtering, our method provides robust and accurate normal vectors across both dense and sparse regions. We integrate this method into a lightweight SLAM framework and evaluate it using indoor LiDAR data from a Velodyne-16 sensor. The results demonstrate improved normal estimation and enhanced localization and mapping performance, highlighting the method's effectiveness for indoor robotic applications.

Cite this

Range-View-Based Normal Estimation for Sparse LiDAR SLAM. / Mortazavi, Faezeh S.; Brenner, Claus; Sester, Monika.
2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN). ed. / Jari Nurmi; Simona Lohan; Aleksandr Ometov; Lucie Klus; Christopher Mutschler; Joaquin Torres-Sospedra. 2025. p. 1-6.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Mortazavi, FS, Brenner, C & Sester, M 2025, Range-View-Based Normal Estimation for Sparse LiDAR SLAM. in J Nurmi, S Lohan, A Ometov, L Klus, C Mutschler & J Torres-Sospedra (eds), 2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN). pp. 1-6. https://doi.org/10.1109/IPIN66788.2025.11213288
Mortazavi, F. S., Brenner, C., & Sester, M. (2025). Range-View-Based Normal Estimation for Sparse LiDAR SLAM. In J. Nurmi, S. Lohan, A. Ometov, L. Klus, C. Mutschler, & J. Torres-Sospedra (Eds.), 2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN) (pp. 1-6) https://doi.org/10.1109/IPIN66788.2025.11213288
Mortazavi FS, Brenner C, Sester M. Range-View-Based Normal Estimation for Sparse LiDAR SLAM. In Nurmi J, Lohan S, Ometov A, Klus L, Mutschler C, Torres-Sospedra J, editors, 2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN). 2025. p. 1-6 doi: 10.1109/IPIN66788.2025.11213288
Mortazavi, Faezeh S. ; Brenner, Claus ; Sester, Monika. / Range-View-Based Normal Estimation for Sparse LiDAR SLAM. 2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN). editor / Jari Nurmi ; Simona Lohan ; Aleksandr Ometov ; Lucie Klus ; Christopher Mutschler ; Joaquin Torres-Sospedra. 2025. pp. 1-6
Download
@inproceedings{cc58049f12274290b4b523a12346e453,
title = "Range-View-Based Normal Estimation for Sparse LiDAR SLAM.",
abstract = "Accurate surface normal estimation is critical for LiDAR-based tasks such as mapping, localization, and scene understanding. However, traditional 3D neighborhood selection methods often struggle with sparse point clouds due to uneven density and sensor limitations. In this paper, we propose a geometry-aware approach that leverages the structured 2D range view to select more consistent neighborhoods for normal estimation. By combining adaptive windowing in range space with distance-based filtering, our method provides robust and accurate normal vectors across both dense and sparse regions. We integrate this method into a lightweight SLAM framework and evaluate it using indoor LiDAR data from a Velodyne-16 sensor. The results demonstrate improved normal estimation and enhanced localization and mapping performance, highlighting the method's effectiveness for indoor robotic applications.",
author = "Mortazavi, {Faezeh S.} and Claus Brenner and Monika Sester",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.",
year = "2025",
month = sep,
day = "15",
doi = "10.1109/IPIN66788.2025.11213288",
language = "English",
isbn = "979-8-3315-5681-5",
pages = "1--6",
editor = "Jari Nurmi and Simona Lohan and Aleksandr Ometov and Lucie Klus and Christopher Mutschler and Joaquin Torres-Sospedra",
booktitle = "2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN)",

}

Download

TY - GEN

T1 - Range-View-Based Normal Estimation for Sparse LiDAR SLAM.

AU - Mortazavi, Faezeh S.

AU - Brenner, Claus

AU - Sester, Monika

N1 - Publisher Copyright: © 2025 IEEE.

PY - 2025/9/15

Y1 - 2025/9/15

N2 - Accurate surface normal estimation is critical for LiDAR-based tasks such as mapping, localization, and scene understanding. However, traditional 3D neighborhood selection methods often struggle with sparse point clouds due to uneven density and sensor limitations. In this paper, we propose a geometry-aware approach that leverages the structured 2D range view to select more consistent neighborhoods for normal estimation. By combining adaptive windowing in range space with distance-based filtering, our method provides robust and accurate normal vectors across both dense and sparse regions. We integrate this method into a lightweight SLAM framework and evaluate it using indoor LiDAR data from a Velodyne-16 sensor. The results demonstrate improved normal estimation and enhanced localization and mapping performance, highlighting the method's effectiveness for indoor robotic applications.

AB - Accurate surface normal estimation is critical for LiDAR-based tasks such as mapping, localization, and scene understanding. However, traditional 3D neighborhood selection methods often struggle with sparse point clouds due to uneven density and sensor limitations. In this paper, we propose a geometry-aware approach that leverages the structured 2D range view to select more consistent neighborhoods for normal estimation. By combining adaptive windowing in range space with distance-based filtering, our method provides robust and accurate normal vectors across both dense and sparse regions. We integrate this method into a lightweight SLAM framework and evaluate it using indoor LiDAR data from a Velodyne-16 sensor. The results demonstrate improved normal estimation and enhanced localization and mapping performance, highlighting the method's effectiveness for indoor robotic applications.

UR - http://www.scopus.com/inward/record.url?scp=105022158714&partnerID=8YFLogxK

U2 - 10.1109/IPIN66788.2025.11213288

DO - 10.1109/IPIN66788.2025.11213288

M3 - Conference contribution

SN - 979-8-3315-5681-5

SP - 1

EP - 6

BT - 2025 International Conference on Indoor Positioning and Indoor Navigation (IPIN)

A2 - Nurmi, Jari

A2 - Lohan, Simona

A2 - Ometov, Aleksandr

A2 - Klus, Lucie

A2 - Mutschler, Christopher

A2 - Torres-Sospedra, Joaquin

ER -

By the same author(s)