mlsanityData to 14 Oct 2026

GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction

arXiv 2409.06685 ↗First posted 10 Sep 2024cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

3D Gaussian Splatting (3DGS) has shown promising performance in novel view synthesis. Previous methods adapt it to obtaining surfaces of either individual 3D objects or within limited scenes. In this paper, we make the first attempt to tackle the challenging task of large-scale scene surface reconstruction. This task is particularly difficult due to the high GPU memory consumption, different levels of details for geometric representation, and noticeable inconsistencies in appearance. To this end, we propose GigaGS, the first work for high-quality surface reconstruction for large-scale scenes using 3DGS. GigaGS first applies a partitioning strategy based on the mutual visibility of spatial regions, which effectively grouping cameras for parallel processing. To enhance the quality of the surface, we also propose novel multi-view photometric and geometric consistency constraints based on Level-of-Detail representation. In doing so, our method can reconstruct detailed surface structures. Comprehensive experiments are conducted on various datasets. The consistent improvement demonstrates the superiority of GigaGS.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 10 Sep 2024.

Builds on

33 of 47 references.

References · 33

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  8. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  9. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  10. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  11. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  12. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
21 more
  1. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  2. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  3. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  4. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  5. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  6. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
  7. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
  8. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  9. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  10. 2023Text-to-3D using Gaussian Splattingcited by 299
  11. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
  12. 2023GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfacescited by 252
  13. 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 230
  14. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  15. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  16. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  17. 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
  18. 2024GVGEN: Text-to-3D Generation with Volumetric Representationcited by 51
  19. 2022iDF-SLAM: End-to-End RGB-D SLAM with Neural Implicit Mapping and Deep Feature Trackingcited by 22
  20. 2024NeRF-XL: Scaling NeRFs with Multiple GPUscited by 19
  21. 2024ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstructioncited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 10; 2026: 4.

20 papers.

Sort:

By area:

  1. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 79
  2. 2024DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenescited by 45
  3. 2025DeepVerse: 4D Autoregressive Video Generation as a World Modelcited by 40
  4. 2024DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusioncited by 38
  5. 2024PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulationcited by 36
  6. 2024Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstructioncited by 28
  7. 2025CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstructioncited by 26
  8. 2025HUG: Hierarchical Urban Gaussian Splatting with Block-Based Reconstruction for Large-Scale Aerial Scenescited by 7
  9. 2024ULSR-GS: Ultra Large-scale Surface Reconstruction Gaussian Splatting with Multi-View Geometric Consistencycited by 6
  10. 2025PG-SAG: Parallel Gaussian Splatting for Fine-Grained Large-Scale Urban Buildings Reconstruction via Semantic-Aware Groupingcited by 4
  11. 2025Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splattingcited by 4
  12. 2025MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenescited by 2
8 more
  1. 2026BlitzGS: City-Scale Gaussian Splatting at Lightning Speedcited by 2
  2. 2024AerialGo: Walking-through City View Generation from Aerial Perspectivescited by 1
  3. 2025RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussianscited by 1
  4. 2026WaterClear-GS: Optical-Aware Gaussian Splatting for Underwater Reconstruction and Restorationcited by 1
  5. 2026Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communicationcited by 1
  6. 2025Perceive-Sample-Compress: Towards Real-Time 3D Gaussian Splattingcited by 0
  7. 2025Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illuminationcited by 0
  8. 2026Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstructioncited by 0