HI-SLAM2：基于几何的高斯SLAM用于快速单目场景重建
HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
AI总结：
HI-SLAM2通过结合单目先验与学习密集SLAM，利用3D高斯散射实现快速准确的单目场景重建，超越现有神经SLAM和RGB-D方法。
摘要：
我们提出了HI-SLAM2，一种具有几何意识的高斯SLAM系统，仅使用RGB输入即可实现快速且准确的单目场景重建。现有神经SLAM或基于3DGS的SLAM方法往往在渲染质量和几何准确性之间进行权衡，我们的研究证明，仅使用RGB输入即可同时实现两者。我们的方法核心思想是通过结合易于获得的单目先验信息与基于学习的密集SLAM，增强几何估计能力，并利用3D高斯散射作为核心地图表示来高效建模场景。在回环闭合时，我们的方法通过高效的位姿图捆绑调整确保实时的全局一致性，并通过显式变形3D高斯单元来实现即时的地图更新。此外，我们引入了一种基于网格的尺度对齐策略，以在先前深度中保持改进的尺度一致性，以获得更精细的深度细节。通过在Replica、ScanNet和ScanNet++上的大量实验，我们证明了在重建和渲染质量上显著优于现有神经SLAM方法，甚至在RGB-D方法上也取得了超越。项目页面和源代码将在https://hi-slam2.github.io/上公开。
英文摘要：
We present HI-SLAM2, a geometry-aware Gaussian SLAM system that achieves fast and accurate monocular scene reconstruction using only RGB input. Existing Neural SLAM or 3DGS-based SLAM methods often trade off between rendering quality and geometry accuracy, our research demonstrates that both can be achieved simultaneously with RGB input alone. The key idea of our approach is to enhance the ability for geometry estimation by combining easy-to-obtain monocular priors with learning-based dense SLAM, and then using 3D Gaussian splatting as our core map representation to efficiently model the scene. Upon loop closure, our method ensures on-the-fly global consistency through efficient pose graph bundle adjustment and instant map updates by explicitly deforming the 3D Gaussian units based on anchored keyframe updates. Furthermore, we introduce a grid-based scale alignment strategy to maintain improved scale consistency in prior depths for finer depth details. Through extensive experiments on Replica, ScanNet, and ScanNet++, we demonstrate significant improvements over existing Neural SLAM methods and even surpass RGB-D-based methods in both reconstruction and rendering quality. The project page and source code will be made available at https://hi-slam2.github.io/.
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。
