MemGS：面向实时SLAM的内存高效Gaussian Splatting
MemGS: Memory-Efficient Gaussian Splatting for Real-Time SLAM
AI总结：
本文提出MemGS，通过基于几何相似性在体素空间合并冗余3D高斯基元以降低GPU内存，并利用Patch-Grid点采样初始化提升渲染质量，实现适用于微型飞行器的实时SLAM。
摘要：
3D Gaussian Splatting (3DGS) 的最新进展对渲染和重建技术产生了重大影响。当前研究主要关注利用高性能桌面GPU提升渲染性能和重建质量，在很大程度上忽略了诸如微型飞行器（MAVs）等嵌入式平台的应用。这些设备计算资源和内存有限，通常面临系统性能与重建质量之间的权衡。本文在GPU内存使用方面改进了现有方法，同时增强了渲染质量。具体而言，为了解决SLAM中冗余的3D Gaussian primitives，我们提出基于几何相似性在voxel space中合并它们。这在不影响系统运行时性能的情况下减少了GPU内存使用。此外，通过Patch-Grid (PG) point sampling初始化3D Gaussian primitives来提高渲染质量，从而能够更准确地建模整个场景。在公开数据集上的定量和定性评估证明了我们改进的有效性。
英文摘要：
Recent advancements in 3D Gaussian Splatting (3DGS) have made a significant impact on rendering and reconstruction techniques. Current research predominantly focuses on improving rendering performance and reconstruction quality using high-performance desktop GPUs, largely overlooking applications for embedded platforms like micro air vehicles (MAVs). These devices, with their limited computational resources and memory, often face a trade-off between system performance and reconstruction quality. In this paper, we improve existing methods in terms of GPU memory usage while enhancing rendering quality. Specifically, to address redundant 3D Gaussian primitives in SLAM, we propose merging them in voxel space based on geometric similarity. This reduces GPU memory usage without impacting system runtime performance. Furthermore, rendering quality is improved by initializing 3D Gaussian primitives via Patch-Grid (PG) point sampling, enabling more accurate modeling of the entire scene. Quantitative and qualitative evaluations on publicly available datasets demonstrate the effectiveness of our improvements.
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。
