mlsanityData to 14 Oct 2026

SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction

arXiv 2412.15400 ↗First posted 19 Dec 2024cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to reconstruct high-quality surfaces from only sparse view input images using Gaussian splatting. In this paper, we propose a novel method called SolidGS to address this problem. We observed that the reconstructed geometry can be severely inconsistent across multi-views, due to the property of Gaussian function in geometry rendering. This motivates us to consolidate all Gaussians by adopting a more solid kernel function, which effectively improves the surface reconstruction quality. With the additional help of geometrical regularization and monocular normal estimation, our method achieves superior performance on the sparse view surface reconstruction than all the Gaussian splatting methods and neural field methods on the widely used DTU, Tanks-and-Temples, and LLFF datasets.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 50 of its 59 references that are in the map. First posted on arXiv 19 Dec 2024.

Builds on

50 of 59 references.

References · 50

  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. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  4. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  6. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  7. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  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. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  12. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
38 more
  1. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  2. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  3. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  4. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  5. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  6. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  7. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  8. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  9. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  10. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  11. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  12. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  13. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 311
  14. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  15. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
  16. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  17. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  18. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  19. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  20. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
  21. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  22. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  23. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  24. 2022Generalizable Patch-Based Neural Renderingcited by 122
  25. 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 104
  26. 2024GES: Generalized Exponential Splatting for Efficient Radiance Field Renderingcited by 92
  27. 2024Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integrationcited by 67
  28. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 62
  29. 2024CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussianscited by 62
  30. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  31. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 37
  32. 2024MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Viewscited by 29
  33. 2023S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfacescited by 21
  34. 2023HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularizationcited by 20
  35. 2024SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearizationcited by 19
  36. 2024LoopSparseGS: Loop Based Sparse-View Friendly Gaussian Splattingcited by 18
  37. 2024DisC-GS: Discontinuity-aware Gaussian Splattingcited by 11
  38. 20242DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Featurescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  2. 2025Multiview Geometric Regularization of Gaussian Splatting for Accurate Radiance Fieldscited by 5
  3. 2025SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generationcited by 5
  4. 2025Sparse-View 3D Reconstruction: Recent Advances and Open Challengescited by 4
  5. 2025Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesiscited by 2
  6. 2025EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesiscited by 2
  7. 2026Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Renderingcited by 2
  8. 2026When 3D Gaussian Splatting Recovers Real Surfacescited by 1
  9. 2026GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstructioncited by 0
  10. 2026Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priorscited by 0
  11. 2026Sparse-GS2Mesh: 3D Gaussian Splatting Guided by Novel Stereo Views and 2DGS for Sparse View Surface Reconstructioncited by 0