计算机视觉
人工智能
计算机科学
运动(物理)
对象(语法)
特征(语言学)
噪音(视频)
动作(物理)
匹配移动
运动估计
作者
Runfa Blark Li,Mahdi Shaghaghi,Keito Suzuki,Xinshuang Liu,Varun Moparthi,Bang Du,Walker Curtis,Martin Renschler,Ki Myung Brian Lee,Nikolay Atanasov,Truong Q. Nguyen
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2026-03-06
卷期号:: 2434-2444
被引量:19
标识
DOI:10.1109/wacv61042.2026.00240
摘要
Simultaneous Localization and Mapping (SLAM) is one of the most important environment-perception and navigation algorithms for computer vision, robotics, and autonomous cars/drones. Hence, high quality and fast mapping becomes a fundamental problem. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, state-of-the-art (SOTA) works introduce GS to SLAM. Compared to classical pointcloud-SLAM, GS-SLAM generates photometric information by learning from input camera views and synthesizing unseen views with high-quality textures. However, these GS-SLAM fail when moving objects occupy the scene that violates the static assumption of bundle adjustment. The failed updates of moving GS affects the static GS and contaminates the full map over the video sequence. Although some efforts have been made by concurrent works to consider moving objects for GS-SLAM, they simply detect and remove the moving regions from GS rendering ("anti" dynamic GS-SLAM), where only the static background could benefit from GS. To this end, we propose the first real-time GS-SLAM, "DynaGSLAM", that achieves high-quality online GS rendering, tracking, motion predictions of moving objects in dynamic scenes while jointly estimating accurate ego motion. Our DynaGSLAM outperforms SOTA static & "Anti" dynamic GS-SLAM on three dynamic real datasets, while keeping speed and memory efficiency in practice. https://blarklee.github.io/dynagslam/
科研通智能强力驱动
Strongly Powered by AbleSci AI