Lune

ICCV2025Top-tier venue

Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction

Zhensheng Yuan, Haozhi Huang, Zhen Xiong, Di Wang, Guanghua Yang

Abstract

We present a framework that enables fast reconstruction and real-time rendering of urban-scale scenes while maintaining robustness against appearance variations across multi-view captures. Our approach begins with scene partitioning for parallel training, employing a visibility-based image selection strategy to optimize training efficiency. A controllable level-of-detail (LOD) strategy explicitly regulates Gaussian density under a user-defined budget, enabling efficient training and rendering while maintaining high visual fidelity. The appearance transformation module mitigates the negative effects of appearance inconsistencies across images while enabling flexible adjustments. Additionally, we utilize enhancement modules, such as depth regularization, scale regularization, and antialiasing, to improve reconstruction fidelity. Experimental results demonstrate that our method effectively reconstructs urban-scale scenes and outperforms previous approaches in both efficiency and quality. The source code is available at: https://yzslab.github.io/REUrbanGS.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes cites NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
  • MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes cites Instant neural graphics primitives with a multiresolution hash encoding
  • MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • Depth Anything V2 cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  • 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Instant neural graphics primitives with a multiresolution hash encoding
  • Sky2Ground: A Benchmark for Site Modeling under Varying Altitude cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale ScenesKehua Chen, Tianlu Mao, Xinzhu Ma, Hao Jiang et al.CVPR 2026 · 2 citations
  2. Sky2Ground: A Benchmark for Site Modeling under Varying AltitudeZengyan Wang, Sirshapan Mitra, Rajat Modi, Hui Xian Grace Lim et al.CVPR 2026

Builds on33

  1. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  2. Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
  3. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
  4. Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao et al.NeurIPS 2024 · 2,305 citations
  5. Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations

Related papers

  1. UrbanGS: Efficient and Scalable Architecture for Geometrically Accurate Large-Scene ReconstructionChangbai Li, Haodong Zhu, Hanlin Chen, Xiuping Liang et al.ICLR 2026 · 1 citation
  2. A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large DatasetsBernhard Kerbl, Andreas Meuleman, Georgios Kopanas, Michael Wimmer et al.SIGGRAPH 2024 · 180 citations
  3. A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene ReconstructionFelix Windisch, Thomas Köhler, Lukas Radl, Mattia D'Urso et al.SIGGRAPH 2026
  4. Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly- ThroughsHaithem Turki, Deva Ramanan, Mahadev SatyanarayananCVPR 2022 · 364 citations
  5. CityGS-X\mathcal{X}: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene ReconstructionYuanyuan Gao, Hao Li, Jiaqi Chen, Zhengyu Zou et al.ICCV 2025 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines