mlsanityData to 7 Oct 2026

ULSR-GS: Ultra Large-scale Surface Reconstruction Gaussian Splatting with Multi-View Geometric Consistency

arXiv 2412.01402 ↗First posted 2 Dec 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

While Gaussian Splatting (GS) demonstrates efficient and high-quality scene rendering and small area surface extraction ability, it falls short in handling large-scale aerial image surface extraction tasks. To overcome this, we present ULSR-GS, a framework dedicated to high-fidelity surface extraction in ultra-large-scale scenes, addressing the limitations of existing GS-based mesh extraction methods. Specifically, we propose a point-to-photo partitioning approach combined with a multi-view optimal view matching principle to select the best training images for each sub-region. Additionally, during training, ULSR-GS employs a densification strategy based on multi-view geometric consistency to enhance surface extraction details. Experimental results demonstrate that ULSR-GS outperforms other state-of-the-art GS-based works on large-scale aerial photogrammetry benchmark datasets, significantly improving surface extraction accuracy in complex urban environments. Project page: https://ulsrgs.github.io.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 68 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

38 of 68 references.

References · 38

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  3. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  4. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  5. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  6. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  7. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  8. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  9. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  10. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  11. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  12. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
26 more
  1. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  2. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  3. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  4. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  5. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 228
  6. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  7. 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 214
  8. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  9. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 199
  10. 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 190
  11. 2023MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyondcited by 185
  12. 2019Point-Based Multi-View Stereo Networkcited by 147
  13. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  14. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 110
  15. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  16. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 99
  17. 2019SampleNet: Differentiable Point Cloud Samplingcited by 74
  18. 2019Planar Prior Assisted PatchMatch Multi-View Stereocited by 57
  19. 2022Real-Time Neural Light Field on Mobile Devicescited by 48
  20. 2024CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenescited by 48
  21. 2021Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Renderingcited by 46
  22. 2024Trim 3D Gaussian Splatting for Accurate Geometry Representationcited by 28
  23. 2024GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRFcited by 21
  24. 2024GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstructioncited by 20
  25. 2024GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereocited by 16
  26. 2024MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densificationcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025EndoFlow-SLAM: Real-Time Endoscopic SLAM with Flow-Constrained Gaussian Splattingcited by 10
  2. 2026Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligencecited by 5
  3. 2025EndoWave: 4D Gaussian Splatting with Rational Wavelet for Endoscopic Reconstructioncited by 4
  4. 2025DentalSplat: Dental Occlusion Novel View Synthesis from Sparse Intra-Oral Photographscited by 3
  5. 2025Time-resolved dynamic CBCT reconstruction using prior-model-free spatiotemporal Gaussian representation (PMF-STGR)cited by 2
  6. 2025A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memorycited by 0