Abstract
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: this https URL.
Abstract (translated)
近年来,神经辐射场(NeRF)已经被广泛应用于作为3D表示同时进行密集定位和映射(SLAM)。尽管NeRF在表面建模和新颖视角合成方面取得了显著的成功,但基于现有NeRF的方法在计算密集和耗时的体积渲染管道方面存在限制。本文提出了一种基于新不确定性和几何稳定性高的新兴3D高斯场,即CG-SLAM,实现高效密集的RGB-D SLAM系统。通过深入分析高斯展开,我们提出了一些方法来构建一个适合跟踪和映射的稳定一致性高斯场。此外,还提出了一种新的深度不确定性模型,在优化过程中确保选择有价值的 Gaussian primitive,从而提高跟踪效率和准确性。在各种数据集上的实验证明CG-SLAM具有卓越的跟踪和映射性能,跟踪速度可以达到高达15Hz。我们将公开源代码。项目页面:此链接。
URL
https://arxiv.org/abs/2403.16095