Geo2DGS‐SLAM: Geometry‐Driven SLAM With 2D Gaussian Splatting
CAAI Transactions on Intelligence Technology · 2026-10 · 11 (5) · 1360-1374
DOI: 10.1049/cit2.70183 ↗Kurz gefasst
Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 21.09.2026. Verfasst von Weiqing Yan und 4 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Recent advances in SLAM systems based on 3D Gaussian Splatting have enabled dense and photorealistic scene reconstruction. However, 3DGS‐based methods still suffer from limited geometric awareness due to the lack of normal rendering support, view inconsistency and weak depth constraints, ultimately hindering high‐fidelity geometric reconstruction and robust pose tracking. In this paper, we present Geo2DGS‐SLAM, a novel dense RGB‐D SLAM framework that uses a geometry‐aware 2D Gaussian representation for scene modelling, featuring a hybrid tracking framework, 2DGS‐based submap construction and a mesh‐binding submap merging strategy. Unlike prior approaches that rely solely on 3DGS appearance modelling, our 2DGS representation enables more accurate rendering of both depth and surface normals, facilitating high‐quality and geometrically consistent reconstruction. To further enhance robustness and global consistency, the hybrid tracking framework integrates local bundle adjustment, loop closure and global bundle adjustment, which jointly mitigate accumulated drift and improve trajectory stability, particularly in long or challenging sequences. Extensive experiments on public indoor RGB‐D datasets demonstrate that Geo2DGS‐SLAM achieves competitive performance in geometry‐aware mapping, rendering fidelity and pose estimation accuracy among recent Gaussian‐based SLAM methods. Codes and additional experimental results will be available at https://github.com/Able1231/Geo2DGS‐SLAM .
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yan, W., Xie, T., Liao, L., Zhou, W., & Tang, C. (2026). Geo2DGS‐SLAM: Geometry‐Driven SLAM With 2D Gaussian Splatting. CAAI Transactions on Intelligence Technology, 11(5), 1360-1374. https://doi.org/10.1049/cit2.70183
Vancouver
Yan W, Xie T, Liao L, Zhou W, Tang C. Geo2DGS‐SLAM: Geometry‐Driven SLAM With 2D Gaussian Splatting. CAAI Transactions on Intelligence Technology. 2026;11(5):1360-1374. doi:10.1049/cit2.70183
BibTeX
@article{Yan2026,
author = {Yan, Weiqing and Xie, Tianhao and Liao, Liang and Zhou, Wujie and Tang, Chang},
title = {Geo2DGS‐SLAM: Geometry‐Driven SLAM With 2D Gaussian Splatting},
journal = {CAAI Transactions on Intelligence Technology},
year = {2026},
volume = {11},
number = {5},
pages = {1360--1374},
doi = {10.1049/cit2.70183}
}
EUVIMED