Wang Li'an, Xu Jian, An Xuan, Ji Yujie, Wu Yuxuan, Ma Zhaoyuan
School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518055, China.
K-CLUB University College, Korea University, Seoul 14779, Republic of Korea.
Sensors (Basel). 2025 Jul 3;25(13):4151. doi: 10.3390/s25134151.
The 3D Gaussian splatting technique demonstrates significant efficiency advantages in real-time scene reconstruction. However, when its initialization process relies on traditional SfM methods (such as COLMAP), there are obvious bottlenecks, such as high computational resource consumption, as well as the decoupling problem between camera pose optimization and map construction. This paper proposes an online 3DGS optimization system based on ROS. Through the design of a loose-coupling architecture, it realizes real-time data interaction between the frontend SfM/SLAM module and backend 3DGS optimization. Using ROS as a middleware, this system can access the keyframe poses and point-cloud data generated by any frontend algorithms (such as ORB-SLAM, COLMAP, etc.). With the help of a dynamic sliding-window strategy and a rendering-quality loss function that combines L1 and SSIM, it achieves online optimization of the 3DGS map. The experimental data shows that compared with the traditional COLMAP-3DGS process, this system reduces the initialization time by 90% and achieves an average PSNR improvement of 1.9 dB on the TUM-RGBD, Tanks and Temples, and KITTI datasets.
3D高斯点渲染技术在实时场景重建中展现出显著的效率优势。然而，当其初始化过程依赖于传统的结构从运动（SfM）方法（如COLMAP）时，存在明显的瓶颈，如高计算资源消耗，以及相机位姿优化与地图构建之间的解耦问题。本文提出了一种基于机器人操作系统（ROS）的在线3D高斯点渲染（3DGS）优化系统。通过设计一种松耦合架构，它实现了前端SfM/同步定位与地图构建（SLAM）模块和后端3DGS优化之间的实时数据交互。使用ROS作为中间件，该系统可以访问由任何前端算法（如ORB-SLAM、COLMAP等）生成的关键帧位姿和点云数据。借助动态滑动窗口策略和结合L1和结构相似性（SSIM）的渲染质量损失函数，它实现了3DGS地图的在线优化。实验数据表明，与传统的COLMAP-3DGS流程相比，该系统将初始化时间减少了90%，并在TUM-RGBD、坦克与庙宇以及KITTI数据集上实现了平均峰值信噪比（PSNR）提高1.9分贝。
