NICER-SLAM : Neural Implicit Scene Encoding for RGB SLAM
(2024) 11th International Conference on 3D Vision, 3DV 2024 p.42-52- Abstract
Neural implicit representations have recently become popular in simultaneous localization and mapping (SLAM), especially in dense visual SLAM. However, existing works either rely on RGB-D sensors or require a separate monocular SLAM approach for camera tracking, and fail to produce high-fidelity 3D dense reconstructions. To address these shortcomings, we present NICER-SLAM, a dense RGB SLAM system that simultaneously optimizes for camera poses and a hierarchical neural implicit map representation, which also allows for high-quality novel view synthesis. To facilitate the optimization process for mapping, we integrate additional supervision signals including easy-to-obtain monocular geometric cues and optical flow, and also introduce a... (More)
Neural implicit representations have recently become popular in simultaneous localization and mapping (SLAM), especially in dense visual SLAM. However, existing works either rely on RGB-D sensors or require a separate monocular SLAM approach for camera tracking, and fail to produce high-fidelity 3D dense reconstructions. To address these shortcomings, we present NICER-SLAM, a dense RGB SLAM system that simultaneously optimizes for camera poses and a hierarchical neural implicit map representation, which also allows for high-quality novel view synthesis. To facilitate the optimization process for mapping, we integrate additional supervision signals including easy-to-obtain monocular geometric cues and optical flow, and also introduce a simple warping loss to further enforce geometric consistency. Moreover, to further boost performance in complex large-scale scenes, we also propose a local adaptive transformation from signed distance functions (SDFs) to density in the volume rendering equation. On multiple challenging indoor and outdoor datasets, NICER-SLAM demonstrates strong performance in dense mapping, novel view synthesis, and tracking, even competitive with recent RGB-D SLAM systems. Project page: https://nicer-slam.github.io/.
(Less)
- author
- Zhu, Zihan ; Peng, Songyou ; Larsson, Viktor LU ; Cui, Zhaopeng ; Oswald, Martin R. ; Geiger, Andreas and Pollefeys, Marc
- organization
- publishing date
- 2024
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- NeRF, neural implicit representation, SLAM
- host publication
- Proceedings - 2024 International Conference on 3D Vision, 3DV 2024
- pages
- 11 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 11th International Conference on 3D Vision, 3DV 2024
- conference location
- Davos, Switzerland
- conference dates
- 2024-03-18 - 2024-03-21
- external identifiers
-
- scopus:85193006230
- ISBN
- 9798350362459
- DOI
- 10.1109/3DV62453.2024.00096
- language
- English
- LU publication?
- yes
- id
- ab0d2da1-1b77-44e4-929c-b85983c1588c
- date added to LUP
- 2025-01-16 10:06:52
- date last changed
- 2025-04-10 09:29:48
@inproceedings{ab0d2da1-1b77-44e4-929c-b85983c1588c,
abstract = {{<p>Neural implicit representations have recently become popular in simultaneous localization and mapping (SLAM), especially in dense visual SLAM. However, existing works either rely on RGB-D sensors or require a separate monocular SLAM approach for camera tracking, and fail to produce high-fidelity 3D dense reconstructions. To address these shortcomings, we present NICER-SLAM, a dense RGB SLAM system that simultaneously optimizes for camera poses and a hierarchical neural implicit map representation, which also allows for high-quality novel view synthesis. To facilitate the optimization process for mapping, we integrate additional supervision signals including easy-to-obtain monocular geometric cues and optical flow, and also introduce a simple warping loss to further enforce geometric consistency. Moreover, to further boost performance in complex large-scale scenes, we also propose a local adaptive transformation from signed distance functions (SDFs) to density in the volume rendering equation. On multiple challenging indoor and outdoor datasets, NICER-SLAM demonstrates strong performance in dense mapping, novel view synthesis, and tracking, even competitive with recent RGB-D SLAM systems. Project page: https://nicer-slam.github.io/.</p>}},
author = {{Zhu, Zihan and Peng, Songyou and Larsson, Viktor and Cui, Zhaopeng and Oswald, Martin R. and Geiger, Andreas and Pollefeys, Marc}},
booktitle = {{Proceedings - 2024 International Conference on 3D Vision, 3DV 2024}},
isbn = {{9798350362459}},
keywords = {{NeRF; neural implicit representation; SLAM}},
language = {{eng}},
pages = {{42--52}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
title = {{NICER-SLAM : Neural Implicit Scene Encoding for RGB SLAM}},
url = {{http://dx.doi.org/10.1109/3DV62453.2024.00096}},
doi = {{10.1109/3DV62453.2024.00096}},
year = {{2024}},
}