优化3D高斯点云内存占用，实现实时SLAM在小型飞行器上的运行
MemGS: Memory-Efficient Gaussian Splatting for Real-Time SLAM
- 在体素空间中合并几何相似的高斯点，减少显存占用
- 通过补丁网格采样初始化点，提升场景重建质量
- 适合资源受限设备如微型无人机的实时三维建图
3D高斯点云渲染与重建技术近年来取得显著进展，但现有研究主要面向高性能桌面级GPU，忽视了微小型飞行器（MAVs）等嵌入式平台的应用。这些设备计算资源和内存有限，常面临性能与重建质量之间的权衡。本文提出一种内存高效的3D高斯点云方法（MemGS），在不降低系统运行效率的前提下，通过在体素空间中基于几何相似性合并冗余的3D高斯点，有效降低显存使用。同时，采用补丁网格（Patch-Grid, PG）点采样方式初始化高斯点，实现更精确的场景建模，从而提升渲染质量。在公开数据集上的定量与定性评估表明，该方法在降低内存消耗的同时显著提升了重建效果。
原文摘要 · Abstract (English)
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.
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。