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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 12776 - 12786
Hlavní autoři: Zhu, Zihan, Peng, Songyou, Larsson, Viktor, Xu, Weiwei, Bao, Hujun, Cui, Zhaopeng, Oswald, Martin R., Pollefeys, Marc
Médium: Konferenční příspěvek Kapitola
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
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
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISBN:9781665469470
1665469463
1665469471
9781665469463
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.01245