Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Kehua, Mao, Tianlu, Ma, Xinzhu, Jiang, Hao, Li, Zehao, Liu, Zihan, Gao, Shuqin, Zhao, Honglong, Dai, Feng, Zhang, Yucheng, Wang, Zhaoqi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.19172
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917402559643648
author Chen, Kehua
Mao, Tianlu
Ma, Xinzhu
Jiang, Hao
Li, Zehao
Liu, Zihan
Gao, Shuqin
Zhao, Honglong
Dai, Feng
Zhang, Yucheng
Wang, Zhaoqi
author_facet Chen, Kehua
Mao, Tianlu
Ma, Xinzhu
Jiang, Hao
Li, Zehao
Liu, Zihan
Gao, Shuqin
Zhao, Honglong
Dai, Feng
Zhang, Yucheng
Wang, Zhaoqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19172
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
Chen, Kehua
Mao, Tianlu
Ma, Xinzhu
Jiang, Hao
Li, Zehao
Liu, Zihan
Gao, Shuqin
Zhao, Honglong
Dai, Feng
Zhang, Yucheng
Wang, Zhaoqi
Computer Vision and Pattern Recognition
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.
title MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.19172