用2D高斯表面元实现高精度稠密建图与追踪，解决视角变化下的几何失真问题。
GauS-SLAM: Dense RGB-D SLAM with Gaussian Surfels
- 采用2D高斯表面元与动态局部地图设计，提升追踪稳定性。
- 在多个数据集上实现更优的追踪精度和渲染保真度。
- 适合需要高精度三维重建的机器人导航与AR应用。
我们提出GauS-SLAM，一种基于2D高斯表面元的稠密RGB-D SLAM系统，旨在实现鲁棒追踪与高保真建图。研究发现，高斯场景表示在新视角下存在几何失真，显著降低追踪准确性，主要源于高斯原语的深度建模及深度融合时的表面相互干扰。为此，我们提出基于2D高斯的增量式重建策略与面向表面的深度渲染机制，显著提升几何精度与多视角一致性。此外，所提出的局部地图设计在追踪中动态隔离可见表面，缓解全局地图中遮挡区域引起的误配准，同时在高斯密度增加时仍保持计算效率。在多个数据集上的大量实验表明，GauS-SLAM优于现有方法，在追踪精度和渲染保真度方面表现卓越。项目页面将发布于https://gaus-slam.github.io。
原文摘要 · Abstract (English)
We propose GauS-SLAM, a dense RGB-D SLAM system that leverages 2D Gaussian surfels to achieve robust tracking and high-fidelity mapping. Our investigations reveal that Gaussian-based scene representations exhibit geometry distortion under novel viewpoints, which significantly degrades the accuracy of Gaussian-based tracking methods. These geometry inconsistencies arise primarily from the depth modeling of Gaussian primitives and the mutual interference between surfaces during the depth blending. To address these, we propose a 2D Gaussian-based incremental reconstruction strategy coupled with a Surface-aware Depth Rendering mechanism, which significantly enhances geometry accuracy and multi-view consistency. Additionally, the proposed local map design dynamically isolates visible surfaces during tracking, mitigating misalignment caused by occluded regions in global maps while maintaining computational efficiency with increasing Gaussian density. Extensive experiments across multiple datasets demonstrate that GauS-SLAM outperforms comparable methods, delivering superior tracking precision and rendering fidelity. The project page will be made available at https://gaus-slam.github.io.
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。