EUVIMEDEUVIMED entdecken
Crossref

EAGS-SLAM: Edge-Assisted Gaussian Splatting SLAM

Hongle Mo, Zifeng Zhao, Yansen Lu, Li Peng, Dongmei Liu, Shaomin Tang, Bingquan Xu, Jian Qiu, Peng Han, Kaiqing Luo

IEEE Sensors Journal · 01.04.2026 · 26 (7) · 10552-10561

DOI: 10.1109/jsen.2026.3663321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.04.2026. Verfasst von Hongle Mo und 9 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing 3-D Gaussian Splatting (3DGS)-based simultaneous localization and mapping (SLAM) methods improve tracking accuracy and rendering quality by incorporating additional components such as loop closure. However, this improvement comes at the cost of reduced speed, and these methods have limited the use of image information. In this article, we propose EAGS-SLAM, an edgeassisted RGB-D Gaussian Splatting SLAM that leverages edge information to improve system performance. EAGSSLAM combines edge-based visual odometry and Gaussian tracking, which reduces camera tracking time by up to 50%. We propose a novel Gaussian seeding method that directly utilizes edge information to capture geometric details in images. A decoupled submap design that can run loop closure in parallel, ensuring globally consistent mapping while improving system speed. The proposed system is evaluated on real-world datasets, ScanNet, TUM RGB-D, and a synthetic dataset Replica. Compared with existing state-of-the-art systems, the proposed system demonstrates competitive or superior performance in tracking, rendering, and runtime. The code and visualization results are available at https://endermands.github.io/EAGSSLAM

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Mo, H., Zhao, Z., Lu, Y., Peng, L., Liu, D., Tang, S., Xu, B., Qiu, J., Han, P., & Luo, K. (2026). EAGS-SLAM: Edge-Assisted Gaussian Splatting SLAM. IEEE Sensors Journal, 26(7), 10552-10561. https://doi.org/10.1109/jsen.2026.3663321

Vancouver

Mo H, Zhao Z, Lu Y, Peng L, Liu D, Tang S, et al. EAGS-SLAM: Edge-Assisted Gaussian Splatting SLAM. IEEE Sensors Journal. 2026;26(7):10552-10561. doi:10.1109/jsen.2026.3663321

BibTeX
@article{Mo2026,
  author = {Mo, Hongle and Zhao, Zifeng and Lu, Yansen and Peng, Li and Liu, Dongmei and Tang, Shaomin and Xu, Bingquan and Qiu, Jian and Han, Peng and Luo, Kaiqing},
  title = {EAGS-SLAM: Edge-Assisted Gaussian Splatting SLAM},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {10552--10561},
  doi = {10.1109/jsen.2026.3663321}
}
Kostenlos starten →