用低成本相机+单线激光雷达，实现高精度室内三维重建。
ES-Gaussian: Gaussian Splatting Mapping via Error Space-Based Gaussian Completion
- 基于二维误差图增强稀疏点云，修复几何细节不足区域。
- 仅需单线激光雷达即可完成3DGS初始化，降低设备依赖。
- 在新数据集和公开数据集上均超越现有方法，适合机器人导航。
高精度且低成本的室内三维重建对机器人导航与交互至关重要。传统激光雷达（LiDAR）虽精度高，但成本高、重量大、功耗高，且难以实现新视角渲染。基于视觉的建图虽成本低、能捕获视觉信息，但常因点云稀疏而难以实现高质量重建。本文提出ES-Gaussian，一种基于低空摄像头与单线激光雷达的端到端系统，实现高质量室内三维重建。系统采用视觉误差构建（VEC）机制，通过二维误差图识别并修正几何细节不足区域，提升点云质量；同时提出一种由单线激光雷达引导的新型3DGS初始化方法，突破传统多视角设置限制，可在资源受限环境中有效运行。在自建的Dreame-SR数据集及公开数据集上的大量实验表明，该方法在复杂场景下显著优于现有方法。项目主页见：https://chenlu-china.github.io/ES-Gaussian/
原文摘要 · Abstract (English)
Accurate and affordable indoor 3D reconstruction is critical for effective robot navigation and interaction. Traditional LiDAR-based mapping provides high precision but is costly, heavy, and power-intensive, with limited ability for novel view rendering. Vision-based mapping, while cost-effective and capable of capturing visual data, often struggles with high-quality 3D reconstruction due to sparse point clouds. We propose ES-Gaussian, an end-to-end system using a low-altitude camera and single-line LiDAR for high-quality 3D indoor reconstruction. Our system features Visual Error Construction (VEC) to enhance sparse point clouds by identifying and correcting areas with insufficient geometric detail from 2D error maps. Additionally, we introduce a novel 3DGS initialization method guided by single-line LiDAR, overcoming the limitations of traditional multi-view setups and enabling effective reconstruction in resource-constrained environments. Extensive experimental results on our new Dreame-SR dataset and a publicly available dataset demonstrate that ES-Gaussian outperforms existing methods, particularly in challenging scenarios. The project page is available at https://chenlu-china.github.io/ES-Gaussian/.
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。