MetroGS：高效稳定重建几何精确的高保真大规模场景
MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
提出分布式2D高斯泼溅作为统一骨干，结合SfM先验与点图模型稠密初始化、渐进混合几何优化和深度引导外观建模，为大规模城市场景的高保真几何重建提供了可复用的稳定框架。
原文依据 we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期，3D高斯泼溅及其衍生方法在大规模场景重建中取得了显著突破。然而，如何高效且稳定地实现高质量的几何保真度仍是一个核心挑战。为解决该问题，我们提出MetroGS，一种用于复杂城市环境中高效鲁棒重建的新型高斯泼溅框架。该方法以分布式2D高斯泼溅表示作为核心基础，并作为后续模块的统一骨干网络。为处理复杂场景中潜在的稀疏区域，我们提出一种结构化稠密增强方案，利用SfM先验和点图模型实现更稠密的初始化，同时引入稀疏性补偿机制以提高重建完整性。此外，我们设计了一种渐进混合几何优化策略，将单目与多视角优化有机结合，以实现高效且准确的几何精化。最后，针对大规模场景中常见的表观不一致问题，我们引入深度引导的表观建模方法，学习具有3D一致性的空间特征，促进几何与表观的有效解耦，并进一步增强重建稳定性。在大规模城市数据集上的实验表明，MetroGS在几何精度和渲染质量上均表现优越，为高保真大规模场景重建提供了统一解决方案。项目页面：https://m3phist0.github.io/MetroGS。
英文原文摘要 1582 字符
Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments. Our method is built upon a distributed 2D Gaussian Splatting representation as the core foundation, serving as a unified backbone for subsequent modules. To handle potential sparse regions in complex scenes, we propose a structured dense enhancement scheme that utilizes SfM priors and a pointmap model to achieve a denser initialization, while incorporating a sparsity compensation mechanism to improve reconstruction completeness. Furthermore, we design a progressive hybrid geometric optimization strategy that organically integrates monocular and multi-view optimization to achieve efficient and accurate geometric refinement. Finally, to address the appearance inconsistency commonly observed in large-scale scenes, we introduce a depth-guided appearance modeling approach that learns spatial features with 3D consistency, facilitating effective decoupling between geometry and appearance and further enhancing reconstruction stability. Experiments on large-scale urban datasets demonstrate that MetroGS achieves superior geometric accuracy, rendering quality, offering a unified solution for high-fidelity large-scale scene reconstruction. Project page: https://m3phist0.github.io/MetroGS.