LiSu: A Dataset and Method for LiDAR Surface Normal Estimation

Bibliographic Details
Title:	LiSu: A Dataset and Method for LiDAR Surface Normal Estimation
Authors:	Malić, Dušan, Fruhwirth-Reisinger, Christian, Schulter, Samuel, Possegger, Horst
Publication Year:	2025
Collection:	Computer Science
Subject Terms:	Computer Science - Computer Vision and Pattern Recognition
More Details:	While surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored. This is caused by the lack of large-scale annotated datasets on the one hand, and lack of methods that can robustly handle the sparse and often noisy LiDAR data in a reasonable time on the other hand. We address these limitations using a traffic simulation engine and present LiSu, the first large-scale, synthetic LiDAR point cloud dataset with ground truth surface normal annotations, eliminating the need for tedious manual labeling. Additionally, we propose a novel method that exploits the spatiotemporal characteristics of autonomous driving data to enhance surface normal estimation accuracy. By incorporating two regularization terms, we enforce spatial consistency among neighboring points and temporal smoothness across consecutive LiDAR frames. These regularizers are particularly effective in self-training settings, where they mitigate the impact of noisy pseudo-labels, enabling robust real-world deployment. We demonstrate the effectiveness of our method on LiSu, achieving state-of-the-art performance in LiDAR surface normal estimation. Moreover, we showcase its full potential in addressing the challenging task of synthetic-to-real domain adaptation, leading to improved neural surface reconstruction on real-world data. Comment: Accepted at CVPR 2025
Document Type:	Working Paper
Access URL:	http://arxiv.org/abs/2503.08601
Accession Number:	edsarx.2503.08601
Database:	arXiv

FullText	Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2503.08601 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20250311&spage=&pages=&title=LiSu: A Dataset and Method for LiDAR Surface Normal Estimation&atitle=LiSu%3A%20A%20Dataset%20and%20Method%20for%20LiDAR%20Surface%20Normal%20Estimation&aulast=Mali%C4%87%2C%20Du%C5%A1an&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries
Header	DbId: edsarx DbLabel: arXiv An: edsarx.2503.08601 RelevancyScore: 1147 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1146.57763671875
IllustrationInfo
Items	– Name: Title Label: Title Group: Ti Data: LiSu: A Dataset and Method for LiDAR Surface Normal Estimation – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Malić%2C+Dušan%22">Malić, Dušan</searchLink><br /><searchLink fieldCode="AR" term="%22Fruhwirth-Reisinger%2C+Christian%22">Fruhwirth-Reisinger, Christian</searchLink><br /><searchLink fieldCode="AR" term="%22Schulter%2C+Samuel%22">Schulter, Samuel</searchLink><br /><searchLink fieldCode="AR" term="%22Possegger%2C+Horst%22">Possegger, Horst</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2025 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink> – Name: Abstract Label: Description Group: Ab Data: While surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored. This is caused by the lack of large-scale annotated datasets on the one hand, and lack of methods that can robustly handle the sparse and often noisy LiDAR data in a reasonable time on the other hand. We address these limitations using a traffic simulation engine and present LiSu, the first large-scale, synthetic LiDAR point cloud dataset with ground truth surface normal annotations, eliminating the need for tedious manual labeling. Additionally, we propose a novel method that exploits the spatiotemporal characteristics of autonomous driving data to enhance surface normal estimation accuracy. By incorporating two regularization terms, we enforce spatial consistency among neighboring points and temporal smoothness across consecutive LiDAR frames. These regularizers are particularly effective in self-training settings, where they mitigate the impact of noisy pseudo-labels, enabling robust real-world deployment. We demonstrate the effectiveness of our method on LiSu, achieving state-of-the-art performance in LiDAR surface normal estimation. Moreover, we showcase its full potential in addressing the challenging task of synthetic-to-real domain adaptation, leading to improved neural surface reconstruction on real-world data.<br />Comment: Accepted at CVPR 2025 – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2503.08601" linkWindow="_blank">http://arxiv.org/abs/2503.08601</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2503.08601
PLink	https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2503.08601
RecordInfo	BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general Titles: – TitleFull: LiSu: A Dataset and Method for LiDAR Surface Normal Estimation Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Malić, Dušan – PersonEntity: Name: NameFull: Fruhwirth-Reisinger, Christian – PersonEntity: Name: NameFull: Schulter, Samuel – PersonEntity: Name: NameFull: Possegger, Horst IsPartOfRelationships: – BibEntity: Dates: – D: 11 M: 03 Type: published Y: 2025
ResultId	1