Qi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qi Li has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Li Zhan
Center for Public Security Technology, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Zhaoqian Jia
Center for Public Security Technology, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication - Zhiguo Wang
Center for Public Security Technology, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication
Latest Publications
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6890-6904
DGS-SLAM: Robust Visual SLAM With 3D Gaussian Splatting in Dynamic Environments
Integrating 3D Gaussian Splatting (3DGS) for dense scene reconstruction has recently gained significant attention in the field of Visual Simultaneous Localization and Mapping (V-SLAM). However, the static scene assumption underlying both V-SLAM and 3DGS limits their effectiveness in real-world environments populated with dynamic objects. Dynamic objects not only degrade SLAM tracking performance but also compromise the spatial-temporal consistency of the reconstructed map, leading to severe system failures. In this work, we propose DGS-SLAM, a novel 3DGS-based V-SLAM system capable of robust self-localization and dense mapping in dynamic environments. To address dynamic scenes, DGS-SLAM integrates several key strategies: 1) object association that fuses visual and geometric information to match objects between adjacent frames; 2) motion check that extends object association to a long-term sliding window to accurately perceive the movement of objects; 3) local fine-tuning that repairs the 3DGS model and updates keyframe poses after eliminating dynamic objects; 4) keyframe selection that promptly selects static keyframes to optimize the static regions in the 3DGS model. Extensive experiments on the TUM RGB-D and BONN RGB-D Dynamic datasets demonstrate that DGS-SLAM significantly improves localization accuracy in dynamic scenes while generating high-quality static maps, compared to other existing state-of-the-art 3DGS-based methods.
- 18 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6890-6904
DGS-SLAM: Robust Visual SLAM With 3D Gaussian Splatting in Dynamic Environments
Integrating 3D Gaussian Splatting (3DGS) for dense scene reconstruction has recently gained significant attention in the field of Visual Simultaneous Localization and Mapping (V-SLAM). However, the static scene assumption underlying both V-SLAM and 3DGS limits their effectiveness in real-world environments populated with dynamic objects. Dynamic objects not only degrade SLAM tracking performance but also compromise the spatial-temporal consistency of the reconstructed map, leading to severe system failures. In this work, we propose DGS-SLAM, a novel 3DGS-based V-SLAM system capable of robust self-localization and dense mapping in dynamic environments. To address dynamic scenes, DGS-SLAM integrates several key strategies: 1) object association that fuses visual and geometric information to match objects between adjacent frames; 2) motion check that extends object association to a long-term sliding window to accurately perceive the movement of objects; 3) local fine-tuning that repairs the 3DGS model and updates keyframe poses after eliminating dynamic objects; 4) keyframe selection that promptly selects static keyframes to optimize the static regions in the 3DGS model. Extensive experiments on the TUM RGB-D and BONN RGB-D Dynamic datasets demonstrate that DGS-SLAM significantly improves localization accuracy in dynamic scenes while generating high-quality static maps, compared to other existing state-of-the-art 3DGS-based methods.