mlsanityData to 14 Oct 2026

Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views

arXiv 2504.20378 ↗First posted 29 Apr 2025cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

We present a Gaussian Splatting method for surface reconstruction using sparse input views. Previous methods relying on dense views struggle with extremely sparse Structure-from-Motion points for initialization. While learning-based Multi-view Stereo (MVS) provides dense 3D points, directly combining it with Gaussian Splatting leads to suboptimal results due to the ill-posed nature of sparse-view geometric optimization. We propose Sparse2DGS, an MVS-initialized Gaussian Splatting pipeline for complete and accurate reconstruction. Our key insight is to incorporate the geometric-prioritized enhancement schemes, allowing for direct and robust geometric learning under ill-posed conditions. Sparse2DGS outperforms existing methods by notable margins while being 2× faster than the NeRF-based fine-tuning approach.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 29 Apr 2025.

Builds on

39 of 50 references.

References · 39

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  3. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  4. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  5. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  6. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  7. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  8. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  9. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  10. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  11. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  12. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
27 more
  1. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
  2. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  3. 2020Consistent Video Depth Estimationcited by 220
  4. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  5. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
  6. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
  7. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  8. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 121
  9. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  10. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 111
  11. 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
  12. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  13. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 62
  14. 2024Feature Splatting: Language-Driven Physics-Based Scene Synthesis and Editingcited by 45
  15. 2019Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistencycited by 40
  16. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 37
  17. 2022RC-MVSNet: Unsupervised Multi-View Stereo with Neural Renderingcited by 30
  18. 2023ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstructioncited by 30
  19. 2024Trim 3D Gaussian Splatting for Accurate Geometry Representationcited by 28
  20. 2023Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenescited by 25
  21. 2024SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearizationcited by 19
  22. 2023C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstructioncited by 18
  23. 2022Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimationcited by 16
  24. 2024GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereocited by 16
  25. 2024Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoningcited by 12
  26. 2024SDGE: Stereo Guided Depth Estimation for 360^circ Camera Setscited by 5
  27. 2025CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 17.

26 papers.

Sort:

By area:

  1. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Priorcited by 10
  2. 2025Multiview Geometric Regularization of Gaussian Splatting for Accurate Radiance Fieldscited by 5
  3. 2025Sparse-View 3D Reconstruction: Recent Advances and Open Challengescited by 4
  4. 2025MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenescited by 2
  5. 2026Benchmarking PhD-Level Coding in 3D Geometric Computer Visioncited by 2
  6. 2025From Volume Rendering to 3D Gaussian Splatting: Theory and Applicationscited by 1
  7. 2026SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Renderingcited by 1
  8. 2026textit4DSurf: High-Fidelity Dynamic Scene Surface Reconstructioncited by 1
  9. 2026VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priorscited by 1
  10. 2026Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstructioncited by 1
  11. 2026HAD: Hallucination-Aware Diffusion Priors for 3D Reconstructioncited by 1
  12. 2026VG2GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformercited by 1
14 more
  1. 2025A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstructioncited by 0
  2. 2025FSFSplatter: Build Surface and Novel Views with Sparse-Views within 2mincited by 0
  3. 2025NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigationcited by 0
  4. 2025SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splattingcited by 0
  5. 2026TreeDGS: Aerial Gaussian Splatting for Distant DBH Measurementcited by 0
  6. 2026The Role of Initialization in 3D Gaussian Splattingcited by 0
  7. 2026VisDom: Sparse Novel View Synthesis with Visible Domain Constraintcited by 0
  8. 2026Improving Sparse-View 3DGS Generalization via Flat Minima Optimizationcited by 0
  9. 2026Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priorscited by 0
  10. 2026G2SR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface Reconstructioncited by 0
  11. 2026GSPotential: Camera Potential Field for Sparse-View 3D Gaussian Splattingcited by 0
  12. 2026TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse viewscited by 0
  13. 2026D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstructioncited by 0
  14. 2026Sparse-GS2Mesh: 3D Gaussian Splatting Guided by Novel Stereo Views and 2DGS for Sparse View Surface Reconstructioncited by 0