HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
IEEE Transactions on Robotics · 2025 · 41 · 6478-6493
DOI: 10.1109/tro.2025.3626627 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2025. Verfasst von Wei Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 87 Literaturangaben. Gefördert von: DFG, German Research Foundation, DAAD program Konrad Zuse Schools of Excellence in Artificial Intelligence, Federal Ministry of Research, Technology.
Abstract (Originalsprache)
We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing neural SLAM or 3DGS-based SLAM methods often tradeoff between rendering quality and geometry accuracy, our research demonstrates that both can be achieved simultaneously with RGB input alone. The key idea of our approach is to enhance the ability for geometry estimation by combining easy-to-obtain monocular priors with learning-based dense SLAM, and then using 3-D Gaussian splatting as our core map representation to efficiently model the scene. Upon loop closure, our method ensures on-the-fly global consistency through efficient pose graph bundle adjustment and instant map updates by explicitly deforming the 3-D Gaussian units based on anchored keyframe updates. Furthermore, we introduce a grid-based scale alignment strategy to maintain improved scale consistency in prior depths for finer depth details. Through extensive experiments on Replica, ScanNet, Waymo Open, ETH3D SLAM and ScanNet++ datasets, we demonstrate significant improvements over existing neural SLAM methods and even surpass RGB-D-based methods in both reconstruction and rendering quality.
Förderung
- DFG, German Research Foundation
- DAAD program Konrad Zuse Schools of Excellence in Artificial Intelligence
- Federal Ministry of Research, Technology
Zitieren
APA
Zhang, W., Cheng, Q., Skuddis, D., Zeller, N., Cremers, D., & Haala, N. (2025). HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction. IEEE Transactions on Robotics, 41, 6478-6493. https://doi.org/10.1109/tro.2025.3626627
Vancouver
Zhang W, Cheng Q, Skuddis D, Zeller N, Cremers D, Haala N. HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction. IEEE Transactions on Robotics. 2025;41:6478-6493. doi:10.1109/tro.2025.3626627
BibTeX
@article{Zhang2025,
author = {Zhang, Wei and Cheng, Qing and Skuddis, David and Zeller, Niclas and Cremers, Daniel and Haala, Norbert},
title = {HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction},
journal = {IEEE Transactions on Robotics},
year = {2025},
volume = {41},
pages = {6478--6493},
doi = {10.1109/tro.2025.3626627}
}
EUVIMED