View in EDS

Gaussian landmarks tracking-based real-time splatting reconstruction model.

Saved in:
Bibliographic Details
Title: Gaussian landmarks tracking-based real-time splatting reconstruction model.
Authors: Zhu, Donglin1 (AUTHOR) zdl_edu@bjtu.edu.cn, Wang, Zhongli1 (AUTHOR) zlwang@bjtu.edu.cn, Fan, Xiaoyang1 (AUTHOR) 23120196@bjtu.edu.cn, Chen, Miao1 (AUTHOR) 23125100@bjtu.edu.cn, Chen, Jiuyu1 (AUTHOR) cjychen@bjtu.edu.cn
Source: Image & Vision Computing. Feb2026, Vol. 166, pN.PAG-N.PAG. 1p.
Subjects: SLAM (Robotics), Position tracking (Virtual reality), Three-dimensional imaging, Real-time computing
Abstract: Real-time and high-quality scene reconstruction remains a critical challenge for robotics applications. 3D Gaussian Splatting (3DGS) demonstrates remarkable capabilities in scene rendering. However, its integration with SLAM systems confronts two critical limitations: (1) slow pose tracking caused by full-frame rendering multiple times, and (2) susceptibility to environmental variations such as illumination variations and motion blur. To alleviate these issues, this paper proposes gaussian landmarks-based real-time reconstruction framework — GLT-SLAM, which composes of a ray casting-driven tracking module, a multi-modal keyframe selector, and an incremental geometric–photometric mapping module. To avoid redundant rendering computations, the tracking module achieves efficient 3D-2D correspondence by encoding Gaussian landmark-emitted rays and fusing attention scores. Furthermore, to enhance the framework's robustness against complex environmental conditions, the keyframe selector balances multiple influencing factors including image quality, tracking uncertainty, information entropy, and feature overlap ratios. Finally, to achieve a compact map representation, the mapping module adds only Gaussian primitives of points, lines, and planes, and performs global map optimization through joint photometric–geometric constraints. Experimental results on the Replica, TUM RGB-D, and BJTU datasets demonstrate that the proposed method achieves a real-time processing rate of over 30 Hz on a platform with an NVIDIA RTX 3090, demonstrating a 19% higher efficiency than the fastest Photo-SLAM method while significantly outperforming other baseline methods in both localization and mapping accuracy. The source code will be available on GitHub. 1 1 https://github.com/robotvision2BJTU/GLT-SLAM. • Our GLT-SLAM achieves real-time tracking at over 30 Hz with an efficient module. • A multi-criteria keyframe selector enhances robustness in varying illumination. • Incremental mapping with joint photometric-geometric BA builds compact 3D maps. • Experiments on multiple datasets show state-of-the-art localization and mapping. [ABSTRACT FROM AUTHOR]
Copyright of Image & Vision Computing is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Real-time and high-quality scene reconstruction remains a critical challenge for robotics applications. 3D Gaussian Splatting (3DGS) demonstrates remarkable capabilities in scene rendering. However, its integration with SLAM systems confronts two critical limitations: (1) slow pose tracking caused by full-frame rendering multiple times, and (2) susceptibility to environmental variations such as illumination variations and motion blur. To alleviate these issues, this paper proposes gaussian landmarks-based real-time reconstruction framework — GLT-SLAM, which composes of a ray casting-driven tracking module, a multi-modal keyframe selector, and an incremental geometric–photometric mapping module. To avoid redundant rendering computations, the tracking module achieves efficient 3D-2D correspondence by encoding Gaussian landmark-emitted rays and fusing attention scores. Furthermore, to enhance the framework's robustness against complex environmental conditions, the keyframe selector balances multiple influencing factors including image quality, tracking uncertainty, information entropy, and feature overlap ratios. Finally, to achieve a compact map representation, the mapping module adds only Gaussian primitives of points, lines, and planes, and performs global map optimization through joint photometric–geometric constraints. Experimental results on the Replica, TUM RGB-D, and BJTU datasets demonstrate that the proposed method achieves a real-time processing rate of over 30 Hz on a platform with an NVIDIA RTX 3090, demonstrating a 19% higher efficiency than the fastest Photo-SLAM method while significantly outperforming other baseline methods in both localization and mapping accuracy. The source code will be available on GitHub. 1 1 https://github.com/robotvision2BJTU/GLT-SLAM. • Our GLT-SLAM achieves real-time tracking at over 30 Hz with an efficient module. • A multi-criteria keyframe selector enhances robustness in varying illumination. • Incremental mapping with joint photometric-geometric BA builds compact 3D maps. • Experiments on multiple datasets show state-of-the-art localization and mapping. [ABSTRACT FROM AUTHOR]
ISSN:02628856
DOI:10.1016/j.imavis.2025.105869