CG-SLAM：在一致性不确定性感知3D高斯场中的高效稠密RGB-D SLAM
CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field
AI总结：
本文提出CG-SLAM，一种基于一致性不确定性感知3D高斯场的高效稠密RGB-D SLAM系统，通过深度不确定性模型优化Gaussian基元选择，实现高达15 Hz的追踪速度及卓越的追踪与建图性能。
摘要：
近期，神经辐射场（NeRF）被广泛用作稠密同时定位与建图（SLAM）的3D表示。尽管在表面建模和新视角合成方面取得了显著成功，但现有的基于NeRF的方法受制于其计算密集且耗时的体渲染流程。本文提出了一种高效的稠密RGB-D SLAM系统，即CG-SLAM，它基于一个具有高一致性和几何稳定性的新型不确定性感知3D高斯场。通过对Gaussian Splatting的深入分析，我们提出了几种技术来构建适用于追踪和建图的一致且稳定的3D高斯场。此外，提出了一种新颖的深度不确定性模型，以确保在优化过程中选择有价值的Gaussian基元，从而提高追踪效率和精度。在多个数据集上的实验表明，CG-SLAM实现了卓越的追踪和建图性能，且追踪速度高达15 Hz。我们将公开源代码。项目页面：https://zju3dv.github.io/cg-slam。
英文摘要：
Recently neural radiance fields (NeRF) have been widely exploited as 3D representations for dense simultaneous localization and mapping (SLAM). Despite their notable successes in surface modeling and novel view synthesis, existing NeRF-based methods are hindered by their computationally intensive and time-consuming volume rendering pipeline. This paper presents an efficient dense RGB-D SLAM system, i.e., CG-SLAM, based on a novel uncertainty-aware 3D Gaussian field with high consistency and geometric stability. Through an in-depth analysis of Gaussian Splatting, we propose several techniques to construct a consistent and stable 3D Gaussian field suitable for tracking and mapping. Additionally, a novel depth uncertainty model is proposed to ensure the selection of valuable Gaussian primitives during optimization, thereby improving tracking efficiency and accuracy. Experiments on various datasets demonstrate that CG-SLAM achieves superior tracking and mapping performance with a notable tracking speed of up to 15 Hz. We will make our source code publicly available. Project page: https://zju3dv.github.io/cg-slam.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
