融合IMU与RGB-D，实现大场景3D高斯点云定位建图
VIGS SLAM: IMU-based Large-Scale 3D Gaussian Splatting SLAM
- 用IMU预积分+ICP框架，降低3D高斯点云追踪计算量
- 在大尺度室内场景中实现媲美顶尖方法的定位精度
- 首个证明高斯点云SLAM可在大场景有效运行的方法
基于辐射场的映射表示（如3D高斯点云和NeRF）因其出色的现实感呈现效果而受到广泛关注，促使研究者尝试将其与SLAM结合。尽管这些方法能构建高度逼真的地图，但在大尺度场景中仍面临挑战，因需大量高斯图像进行建图，且相邻图像作为关键帧用于跟踪。本文提出一种新型3D高斯点云SLAM方法——VIGS SLAM，利用RGB-D与IMU传感器融合，在大尺度室内环境中实现高效建图。为降低3DGS跟踪的计算负担，采用基于ICP的跟踪框架，并融合IMU预积分提供良好初始估计以实现精准位姿估计。本方法首次证明，通过集成IMU测量，基于高斯点云的SLAM可有效应用于大尺度环境。该方案不仅将高斯点云SLAM性能拓展至超房间尺度，还在大尺度室内场景中达到与当前最优方法相当的定位性能。
原文摘要 · Abstract (English)
Recently, map representations based on radiance fields such as 3D Gaussian Splatting and NeRF, which excellent for realistic depiction, have attracted considerable attention, leading to attempts to combine them with SLAM. While these approaches can build highly realistic maps, large-scale SLAM still remains a challenge because they require a large number of Gaussian images for mapping and adjacent images as keyframes for tracking. We propose a novel 3D Gaussian Splatting SLAM method, VIGS SLAM, that utilizes sensor fusion of RGB-D and IMU sensors for large-scale indoor environments. To reduce the computational load of 3DGS-based tracking, we adopt an ICP-based tracking framework that combines IMU preintegration to provide a good initial guess for accurate pose estimation. Our proposed method is the first to propose that Gaussian Splatting-based SLAM can be effectively performed in large-scale environments by integrating IMU sensor measurements. This proposal not only enhances the performance of Gaussian Splatting SLAM beyond room-scale scenarios but also achieves SLAM performance comparable to state-of-the-art methods in large-scale indoor environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。