NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over- smoothed scene reconstructions and have difficulty scaling up to large scenes. These...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 12776 - 12786
Main Authors: Zhu, Zihan, Peng, Songyou, Larsson, Viktor, Xu, Weiwei, Bao, Hujun, Cui, Zhaopeng, Oswald, Martin R., Pollefeys, Marc
Format: Conference Proceeding Book Chapter
Language:English
Published: IEEE 01.06.2022
Subjects:
3D from multi-view and sensors; RGBD sensors and analytics
Cameras
Computer and Information Sciences
Computer graphics and computer vision
Computer vision
Data- och informationsvetenskap (Datateknik)
Datorgrafik och datorseende
Geometry
Natural Sciences
Naturvetenskap
Network architecture
Scalability
Simultaneous localization and mapping
Visualization
ISBN:9781665469470, 1665469463, 1665469471, 9781665469463
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over- smoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. In this paper, we present NICE-SLAM, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation. Optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes. Compared to recent neural implicit SLAM systems, our approach is more scalable, efficient, and robust. Experiments on five challenging datasets demonstrate competitive results of NICE-SLAM in both mapping and tracking quality. Project page: https://pengsongyou.github.io/nice-slam.
AbstractList Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over- smoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. In this paper, we present NICE-SLAM, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation. Optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes. Compared to recent neural implicit SLAM systems, our approach is more scalable, efficient, and robust. Experiments on five challenging datasets demonstrate competitive results of NICE-SLAM in both mapping and tracking quality.
Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over- smoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. In this paper, we present NICE-SLAM, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation. Optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes. Compared to recent neural implicit SLAM systems, our approach is more scalable, efficient, and robust. Experiments on five challenging datasets demonstrate competitive results of NICE-SLAM in both mapping and tracking quality. Project page: https://pengsongyou.github.io/nice-slam.
Author Zhu, Zihan
Pollefeys, Marc
Xu, Weiwei
Peng, Songyou
Bao, Hujun
Larsson, Viktor
Cui, Zhaopeng
Oswald, Martin R.
Author_xml – sequence: 1
  givenname: Zihan
  surname: Zhu
  fullname: Zhu, Zihan
  organization: State Key Lab of CAD&CG, Zhejiang University
– sequence: 2
  givenname: Songyou
  surname: Peng
  fullname: Peng, Songyou
  organization: ETH Zurich
– sequence: 3
  givenname: Viktor
  surname: Larsson
  fullname: Larsson, Viktor
  organization: Lund University
– sequence: 4
  givenname: Weiwei
  surname: Xu
  fullname: Xu, Weiwei
  organization: State Key Lab of CAD&CG, Zhejiang University
– sequence: 5
  givenname: Hujun
  surname: Bao
  fullname: Bao, Hujun
  organization: State Key Lab of CAD&CG, Zhejiang University
– sequence: 6
  givenname: Zhaopeng
  surname: Cui
  fullname: Cui, Zhaopeng
  organization: State Key Lab of CAD&CG, Zhejiang University
– sequence: 7
  givenname: Martin R.
  surname: Oswald
  fullname: Oswald, Martin R.
  organization: ETH Zurich
– sequence: 8
  givenname: Marc
  surname: Pollefeys
  fullname: Pollefeys, Marc
  organization: ETH Zurich
BookMark eNo9jslOw0AQRIdNIoR8ARz8Aw7dszc3FAWIFBYR4DrqccZgZOzIToT4e4JYTlVSlerVkdhv2iYJcYowRgQ6mzzfPxhpvR9LkHIMKLXZEUdordGWtFW7YoBgVW4JaU-MyPm_zMGhGPX9GwAoiWjJD4S5nU2m-WJ-cXOe3aZNx3U2e1_VVVGts0XBNcc6ZdOmaJdV85KVbZd9d4_FQcl1n0a_OhRPl9PHyXU-v7uaTS7meSVJrXMqLDNZY0rpwKCGZeE0sgdySRpYuugiE2DUgB5SKctEZWJtjIqF1loNBf_s9h9ptYlh1VXv3H2Glquwars116FLfeKueA31JvQpbFvb87yu2qYPyMSxMDEYJX3QkDBQhK1bEkGp0Slrt4yTH0aVUvonkHeeUKovHddqXA
CODEN IEEPAD
ContentType Conference Proceeding
Book Chapter
CorporateAuthor Matematik LTH
Research groups at the Centre for Mathematical Sciences
Lunds universitet
LTH profilområden
Profile areas and other strong research environments
Naturvetenskapliga fakulteten
Faculty of Engineering, LTH
Lunds Tekniska Högskola
Faculty of Science
Lund University
LTH Profile areas
ELLIIT: the Linköping-Lund initiative on IT and mobile communication
Strategiska forskningsområden (SFO)
LTH Profile Area: AI and Digitalization
Centre for Mathematical Sciences
Forskargrupper vid Matematikcentrum
Strategic research areas (SRA)
Mathematical Imaging Group
Matematikcentrum
Mathematics (Faculty of Engineering)
LTH profilområde: AI och digitalisering
Profilområden och andra starka forskningsmiljöer
CorporateAuthor_xml – name: ELLIIT: the Linköping-Lund initiative on IT and mobile communication
– name: Strategiska forskningsområden (SFO)
– name: Naturvetenskapliga fakulteten
– name: Mathematics (Faculty of Engineering)
– name: LTH Profile Area: AI and Digitalization
– name: Research groups at the Centre for Mathematical Sciences
– name: Strategic research areas (SRA)
– name: Lunds Tekniska Högskola
– name: Lunds universitet
– name: Faculty of Science
– name: Faculty of Engineering, LTH
– name: Profilområden och andra starka forskningsmiljöer
– name: LTH Profile areas
– name: LTH profilområden
– name: Lund University
– name: LTH profilområde: AI och digitalisering
– name: Matematik LTH
– name: Centre for Mathematical Sciences
– name: Profile areas and other strong research environments
– name: Forskargrupper vid Matematikcentrum
– name: Mathematical Imaging Group
– name: Matematikcentrum
DBID 6IE
6IH
CBEJK
RIE
RIO
ADTPV
BMRNB
BNKNJ
D95
DOI 10.1109/CVPR52688.2022.01245
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP) 1998-present
SwePub
SwePub Book Chapter
SwePub Conference
SWEPUB Lunds universitet
DatabaseTitleList

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665469463
9781665469463
EISSN 1063-6919
EndPage 12786
ExternalDocumentID oai_portal_research_lu_se_publications_1a9abc5b_5328_40e1_9b08_4d990f417366
9878912
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
6IF
6IG
ABQGA
ADTPV
BMRNB
BNKNJ
D95
RIB
RIC
ID FETCH-LOGICAL-i293t-9c6aa9655f2705140dc741a8097e250d7b7ba901b40180ef2fe9fea4553bc4443
IEDL.DBID RIE
ISBN 9781665469470
1665469463
1665469471
9781665469463
ISICitedReferencesCount 481
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000870759105084&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Mon Dec 01 03:11:38 EST 2025
Wed Aug 27 02:15:10 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i293t-9c6aa9655f2705140dc741a8097e250d7b7ba901b40180ef2fe9fea4553bc4443
PageCount 11
ParticipantIDs ieee_primary_9878912
swepub_primary_oai_portal_research_lu_se_publications_1a9abc5b_5328_40e1_9b08_4d990f417366
PublicationCentury 2000
PublicationDate 2022-June
2022
PublicationDateYYYYMMDD 2022-06-01
2022-01-01
PublicationDate_xml – month: 06
  year: 2022
  text: 2022-June
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
ssib049870834
Score 2.6778126
Snippet Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and...
SourceID swepub
ieee
SourceType Open Access Repository
Publisher
StartPage 12776
SubjectTerms 3D from multi-view and sensors; RGBD sensors and analytics
Cameras
Computer and Information Sciences
Computer graphics and computer vision
Computer vision
Data- och informationsvetenskap (Datateknik)
Datorgrafik och datorseende
Geometry
Natural Sciences
Naturvetenskap
Network architecture
Scalability
Simultaneous localization and mapping
Visualization
Title NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
URI https://ieeexplore.ieee.org/document/9878912
WOSCitedRecordID wos000870759105084&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61ePDkoxXrixw8uu0-kk3iTUqLhVqKj1K8hCSbxULZSrv19zvJLlXEi7dAsg8mm51vJvN9QehGcGM44SSgGawmgNQ20IZFQWqZ15cSiU_mzMZsMuHzuZg20O2OC2Ot9cVntuuafi8_W5mtS5X1ID7mwh0pvMcYq7hau3xKApFMKnjNjotC0evPpk9OzMQVcMVxF_7EjrPkz1D5pQvqfcnw8H9vcYTa36Q8PN25m2PUsMUJOqxRJK7X6KaF6GTUHwTP4_vHO-ykN9QSj3zZ-KKEUWrpuFJ4UJiVuw0GzIrd2DZ6HQ5e-g9BfThCsAAPXQbCpEqJlNI8Zk7DPMwMgAPFQ8EswJqMaaYVOHtNnESXzePcitwqQmmiDSEkOUXNYlXYM4RNRimELYDdOHRoIyKl3TZvmNHIQqDaQS1nBflR6V_I2gAd9FYZcdfhpKqrqEHWUkXvcrmVG7j0Rw5SRkoobaiWNIm5JKGNpNAhtDJwjTmJWJKm538_8wIduMmsarUuUbNcb-0V2jef5WKzvvZfxBcvPLQA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFA5DBX2auonz2gcf7dZL0ia-ydjYsCtD5xi-hCRNcTA62Tp_vydtqSK--BZIeuGk6fnOyfm-IHTHqFIUU2yTBFYTQGptSxW6dqDDQl-K-UUyZx6FcUwXCzZtoPuaC6O1LorPdNc0i738ZK12JlXWg_iYMnOk8D7B2HNLtladUfEhlgkYrfhxrsN6_fn02ciZmBIuz-vCv9iwlopTVH4pgxbeZNj833sco_Y3Lc-a1g7nBDV0doqaFY60qlW6bSESj_sD-yV6nDxYRnxDrKxxUTi-zGGUWBm2lDXI1NrcxgLUapmxbfQ6HMz6I7s6HsFego_ObaYCIVhASOqFRsXcSRTAA0EdFmoANkkoQynA3UtsRLp06qWapVpgQnypMMb-GdrL1pk-R5ZKCIHABdAbhQ6pmCuk2eh1EuJqCFU7qGWswD9KBQxeGaCD3koj1h1GrLqMG3glVvTOVzu-hUt_ZCG5K5iQikhOfI9y7GiXM-lAKwHnmGI39IPg4u9n3qLD0WwS8WgcP12iIzOxZeXWFdrLNzt9jQ7UZ77cbm6Kr-MLuRG3Rw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=bookitem&rft.title=Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.au=Zhu%2C+Zihan&rft.au=Peng%2C+Songyou&rft.au=Larsson%2C+Viktor&rft.au=Xu%2C+Weiwei&rft.atitle=NICE-SLAM%3A+Neural+Implicit+Scalable+Encoding+for+SLAM&rft.date=2022-01-01&rft.isbn=9781665469470&rft.spage=12786&rft_id=info:doi/10.1109%2FCVPR52688.2022.01245&rft.externalDocID=oai_portal_research_lu_se_publications_1a9abc5b_5328_40e1_9b08_4d990f417366
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781665469470/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781665469470/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781665469470/sc.gif&client=summon&freeimage=true