mlsanityData to 13 Oct 2026

MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densification

arXiv 2407.11840 ↗First posted 16 Jul 2024cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

In the rapidly evolving field of 3D reconstruction, 3D Gaussian Splatting (3DGS) and 2D Gaussian Splatting (2DGS) represent significant advancements. Although 2DGS compresses 3D Gaussian primitives into 2D Gaussian surfels to effectively enhance mesh extraction quality, this compression can potentially lead to a decrease in rendering quality. Additionally, unreliable densification processes and the calculation of depth through the accumulation of opacity can compromise the detail of mesh extraction. To address this issue, we introduce MVG-Splatting, a solution guided by Multi-View considerations. Specifically, we integrate an optimized method for calculating normals, which, combined with image gradients, helps rectify inconsistencies in the original depth computations. Additionally, utilizing projection strategies akin to those in Multi-View Stereo (MVS), we propose an adaptive quantile-based method that dynamically determines the level of additional densification guided by depth maps, from coarse to fine detail. Experimental evidence demonstrates that our method not only resolves the issues of rendering quality degradation caused by depth discrepancies but also facilitates direct mesh extraction from dense Gaussian point clouds using the Marching Cubes algorithm. This approach significantly enhances the overall fidelity and accuracy of the 3D reconstruction process, ensuring that both the geometric details and visual quality.

Key facts. Cited by 16 papers in the map (data through 13 Oct 2026). Builds on 37 of its 59 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

37 of 59 references.

References · 37

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,170
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,712
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,021
  4. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,958
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,610
  6. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,070
  7. 2021Volume Rendering of Neural Implicit Surfacescited by 992
  8. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 858
  9. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 782
  10. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 721
  11. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 690
  12. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 663
25 more
  1. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 644
  2. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 613
  3. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 557
  4. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  5. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  6. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 283
  7. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  8. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  9. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 199
  10. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  11. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 173
  12. 2019Point-Based Multi-View Stereo Networkcited by 147
  13. 2023Multi-Scale 3D Gaussian Splatting for Anti-Aliased Renderingcited by 137
  14. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  15. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  16. 2017Learning non-maximum suppressioncited by 113
  17. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 110
  18. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  19. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  20. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  21. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 66
  22. 2024SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasingcited by 40
  23. 2024GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereocited by 16
  24. 2023Unsupervised OmniMVS: Efficient Omnidirectional Depth Inference via Establishing Pseudo-Stereo Supervisioncited by 8
  25. 2024GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraintscited by 3

Built on by

Cited by year (2026 to 13 Oct)

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

16 papers.

Sort:

By area:

  1. 2024Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-order Geometric Primitivescited by 20
  2. 2024Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussianscited by 14
  3. 2025GauSTAR: Gaussian Surface Tracking and Reconstructioncited by 13
  4. 2025Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splattingcited by 12
  5. 2024ULSR-GS: Ultra Large-scale Surface Reconstruction Gaussian Splatting with Multi-View Geometric Consistencycited by 6
  6. 2024Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Renderingcited by 5
  7. 2025Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splattingcited by 5
  8. 2025SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstructioncited by 4
  9. 2025Sparse-View 3D Reconstruction: Recent Advances and Open Challengescited by 3
  10. 2025FeatureGS: Eigenvalue-Feature Optimization in 3D Gaussian Splatting for Geometrically Accurate and Artifact-Reduced Reconstructioncited by 1
  11. 2026Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splattingcited by 1
  12. 2026RefGlass-GS: A UAV-Enabled Fusion Framework for Photorealistic, Semantic and Interactive Digitization of Reflective Glass Facades via Gaussian Splattingcited by 0
4 more
  1. 2026Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstructioncited by 0
  2. 2026SkyAnchor: Updating Metric-scale Aerial 3D Gaussian Scenes from Unposed Ground-View Sequencescited by 0
  3. 2026Robust 3D Reconstruction from Multi-View Optical Satellite Imagery via Reliability-Aware Height-Evidence Fusion in Gaussian Splattingcited by 0
  4. 2026Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flowscited by 0