RP-SLAM: 基于高效3D高斯泼溅的实时照片级真实感SLAM
RP-SLAM: Real-time Photorealistic SLAM with Efficient 3D Gaussian Splatting
AI总结：
针对3DGS集成到SLAM中存在的基元冗余、遗忘问题及单目初始化难的问题，提出包含增量建图、动态窗口优化、单目关键帧初始化的RP-SLAM，在保证实时性和模型紧凑性的同时实现了SOTA的地图渲染精度。
摘要：
3D高斯泼溅（3D Gaussian Splatting）已成为高质量3D渲染的一项极具前景的技术，引发了将3DGS集成到真实感SLAM系统中的越来越多的研究兴趣。然而现有方法面临着高斯基元冗余、连续优化过程中的遗忘问题，以及单目场景下因缺乏深度信息导致基元初始化困难等挑战。为实现高效且具有照片级真实感的建图，我们提出RP-SLAM，这是一种适用于单目和RGB-D相机的基于3D高斯泼溅的视觉SLAM方法。RP-SLAM将相机位姿估计与高斯基元优化解耦，包含三个核心组件：首先，我们提出一种高效的增量式建图方法，通过自适应采样和高斯基元滤波实现场景的紧凑且准确的表示；其次，提出动态窗口优化方法以缓解遗忘问题并提升地图一致性；最后，针对单目场景，提出基于稀疏点云的单目关键帧初始化方法，以提高高斯基元的初始化精度，为后续优化提供几何基础。大量实验结果表明，RP-SLAM在保证实时性能和模型紧凑性的同时，达到了当前最优的地图渲染精度。
英文摘要：
3D Gaussian Splatting has emerged as a promising technique for high-quality 3D rendering, leading to increasing interest in integrating 3DGS into realism SLAM systems. However, existing methods face challenges such as Gaussian primitives redundancy, forgetting problem during continuous optimization, and difficulty in initializing primitives in monocular case due to lack of depth information. In order to achieve efficient and photorealistic mapping, we propose RP-SLAM, a 3D Gaussian splatting-based vision SLAM method for monocular and RGB-D cameras. RP-SLAM decouples camera poses estimation from Gaussian primitives optimization and consists of three key components. Firstly, we propose an efficient incremental mapping approach to achieve a compact and accurate representation of the scene through adaptive sampling and Gaussian primitives filtering. Secondly, a dynamic window optimization method is proposed to mitigate the forgetting problem and improve map consistency. Finally, for the monocular case, a monocular keyframe initialization method based on sparse point cloud is proposed to improve the initialization accuracy of Gaussian primitives, which provides a geometric basis for subsequent optimization. The results of numerous experiments demonstrate that RP-SLAM achieves state-of-the-art map rendering accuracy while ensuring real-time performance and model compactness.
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。
