ES-Gaussian

Paper

Supplementary

Arxiv

Code(Soon)

Video

Abstract

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 to do the 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 both our new Dreame-SR dataset and the publicly available dataset demonstrate that ES-Gaussian outperforms existing methods, particularly in challenging scenarios.

Citation

          @misc{chen2024esgaussiangaussiansplattingmapping,
            title={ES-Gaussian: Gaussian Splatting Mapping via Error Space-Based Gaussian Completion}, 
            author={Lu Chen and Yingfu Zeng and Haoang Li and Zhitao Deng and Jiafu Yan and Zhenjun Zhao},
            year={2024},
            eprint={2410.06613},
            archivePrefix={arXiv},
            primaryClass={cs.CV},
            url={https://arxiv.org/abs/2410.06613}, 
          }

The video was made by the authors using Blender and Adobe Premiere Pro. The interactive world map is based on d3.js. For the mesh visualization we use three.js.