mlsanityData to 14 Oct 2026

Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction

arXiv 2507.23006 ↗First posted 30 Jul 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 46 of its 57 references that are in the map. First posted on arXiv 30 Jul 2025.

Builds on

46 of 57 references.

References · 46

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  6. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  8. 2024Depth Anything V2cited by 1,422
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  11. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  12. 2021Volume Rendering of Neural Implicit Surfacescited by 996
34 more
  1. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  2. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  3. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  4. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  5. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  6. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  8. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  9. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  10. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
  11. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  12. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  13. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  14. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  15. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 239
  16. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 229
  17. 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 216
  18. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  19. 2024HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compressioncited by 209
  20. 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 204
  21. 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 192
  22. 2023Compact 3D Scene Representation via Self-Organizing Gaussian Gridscited by 151
  23. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  24. 2024Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detectioncited by 122
  25. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 118
  26. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  27. 2024StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Renderingcited by 111
  28. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 100
  29. 2024SWAG: Splatting in the Wild images with Appearance-conditioned Gaussianscited by 61
  30. 2024SpotlessSplats: Ignoring Distractors in 3D Gaussian Splattingcited by 61
  31. 2024On Scaling Up 3D Gaussian Splatting Trainingcited by 49
  32. 2019AADS: Augmented Autonomous Driving Simulation using Data-driven Algorithmscited by 39
  33. 2023Efficient Large-scale Scene Representation with a Hybrid of High-resolution Grid and Plane Featurescited by 36
  34. 2023SC-NeRF: Self-Correcting Neural Radiance Field with Sparse Viewscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2026TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstructioncited by 11
  2. 2026You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenescited by 4
  3. 2026Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrievalcited by 3
  4. 2025LoBE-GS: Load-Balanced and Efficient 3D Gaussian Splatting for Large-Scale Scene Reconstructioncited by 2
  5. 2025MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenescited by 2
  6. 2026Sky2Ground: A Benchmark for Site Modeling under Varying Altitudecited by 1
  7. 2026City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completioncited by 1
  8. 2026PUGS: Physics-Guided Uncertainty Modeling for Underwater Dynamic 3D Gaussian Splattingcited by 0