Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Zhu, Zihan ; Peng, Songyou ; Larsson, Viktor LU ; Xu, Weiwei ; Bao, Hujun ; Cui, Zhaopeng ; Oswald, Martin R and Pollefeys, Marc (2022) 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 p.12786-12796
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... (More)
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. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
pages
11 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
conference location
New Orleans, United States
conference dates
2022-06-19 - 2022-06-24
external identifiers
  • scopus:85141811894
ISBN
978-1-6654-6946-3
978-1-6654-6947-0
DOI
10.1109/CVPR52688.2022.01245
language
English
LU publication?
yes
id
1a9abc5b-5328-40e1-9b08-4d990f417366
date added to LUP
2022-09-06 13:24:25
date last changed
2024-06-14 21:47:25
@inproceedings{1a9abc5b-5328-40e1-9b08-4d990f417366,
  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.}},
  author       = {{Zhu, Zihan and Peng, Songyou and Larsson, Viktor and Xu, Weiwei and Bao, Hujun and Cui, Zhaopeng and Oswald, Martin R and Pollefeys, Marc}},
  booktitle    = {{Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}},
  isbn         = {{978-1-6654-6946-3}},
  language     = {{eng}},
  pages        = {{12786--12796}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{NICE-SLAM: Neural Implicit Scalable Encoding for SLAM}},
  url          = {{http://dx.doi.org/10.1109/CVPR52688.2022.01245}},
  doi          = {{10.1109/CVPR52688.2022.01245}},
  year         = {{2022}},
}