mlsanityData to 14 Oct 2026

SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting

arXiv 2507.15602 ↗First posted 21 Jul 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Surface reconstruction and novel view rendering from sparse-view images are challenging. Signed Distance Function (SDF)-based methods struggle with fine details, while 3D Gaussian Splatting (3DGS)-based approaches lack global geometry coherence. We propose a novel hybrid method that combines the strengths of both approaches: SDF captures coarse geometry to enhance 3DGS-based rendering, while newly rendered images from 3DGS refine the details of SDF for accurate surface reconstruction. As a result, our method surpasses state-of-the-art approaches in surface reconstruction and novel view synthesis on the DTU and MobileBrick datasets. Code will be released at https://github.com/aim-uofa/SurfaceSplat.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 49 of its 60 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

49 of 60 references.

References · 49

  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. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  10. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  11. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  12. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
37 more
  1. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  2. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  3. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  4. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  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. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  8. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  9. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  10. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  11. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  12. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
  13. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  14. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  15. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 232
  16. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  17. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
  18. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 144
  19. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  20. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  21. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
  22. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  23. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 111
  24. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 94
  25. 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
  26. 20243DGSR: Implicit Surface Reconstruction with 3D Gaussian Splattingcited by 79
  27. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 62
  28. 2024SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasingcited by 41
  29. 2024360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roamingcited by 35
  30. 2024Spectrally Pruned Gaussian Fields with Neural Compensationcited by 33
  31. 2023ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstructioncited by 30
  32. 2023PoRF: Pose Residual Field for Accurate Neural Surface Reconstructioncited by 19
  33. 2024SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearizationcited by 19
  34. 2023MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devicescited by 15
  35. 2024From NeRFs to Gaussian Splats, and Backcited by 6
  36. 2024Integrating Meshes and 3D Gaussians for Indoor Scene Reconstruction with SAM Mask Guidancecited by 4
  37. 2024Enhancement of 3D Gaussian Splatting using Raw Mesh for Photorealistic Recreation of Architecturescited by 1

Built on by

Cited by year (2026 to 14 Oct)

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

6 papers.

  1. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  2. 2026TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstructioncited by 3
  3. 2025Efficient Construction of Implicit Surface Models From a Single Image for Motion Generationcited by 0
  4. 2026NeVStereo: A NeRF-Driven NVS-Stereo Architecture for High-Fidelity 3D Taskscited by 0
  5. 2026City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Imagescited by 0
  6. 2026Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarioscited by 0