mlsanityData to 14 Oct 2026

Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set

arXiv 2410.14189 ↗First posted 18 Oct 2024cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

It is vital to infer a signed distance function (SDF) in multi-view based surface reconstruction. 3D Gaussian splatting (3DGS) provides a novel perspective for volume rendering, and shows advantages in rendering efficiency and quality. Although 3DGS provides a promising neural rendering option, it is still hard to infer SDFs for surface reconstruction with 3DGS due to the discreteness, the sparseness, and the off-surface drift of 3D Gaussians. To resolve these issues, we propose a method that seamlessly merge 3DGS with the learning of neural SDFs. Our key idea is to more effectively constrain the SDF inference with the multi-view consistency. To this end, we dynamically align 3D Gaussians on the zero-level set of the neural SDF using neural pulling, and then render the aligned 3D Gaussians through the differentiable rasterization. Meanwhile, we update the neural SDF by pulling neighboring space to the pulled 3D Gaussians, which progressively refine the signed distance field near the surface. With both differentiable pulling and splatting, we jointly optimize 3D Gaussians and the neural SDF with both RGB and geometry constraints, which recovers more accurate, smooth, and complete surfaces with more geometry details. Our numerical and visual comparisons show our superiority over the state-of-the-art results on the widely used benchmarks.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 64 of its 79 references that are in the map. First posted on arXiv 18 Oct 2024.

Builds on

64 of 79 references.

References · 64

  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. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  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. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  9. 2020Convolutional Occupancy Networkscited by 761
  10. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  11. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  12. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
38 more
  1. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  2. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  3. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  4. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  5. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  6. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  7. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  8. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 221
  9. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
  10. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  11. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 164
  12. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  13. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  14. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  15. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  16. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
  17. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  18. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  19. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  20. 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
  21. 20243DGSR: Implicit Surface Reconstruction with 3D Gaussian Splattingcited by 79
  22. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 76
  23. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  24. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 67
  25. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  26. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 63
  27. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  28. 2022Critical Regularizations for Neural Surface Reconstruction in the Wildcited by 52
  29. 2022Fast Learning Radiance Fields by Shooting Much Fewer Rayscited by 38
  30. 2022NeAF: Learning Neural Angle Fields for Point Normal Estimationcited by 38
  31. 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matchingcited by 37
  32. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 37
  33. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  34. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 33
  35. 2022GenSDF: Two-Stage Learning of Generalizable Signed Distance Functionscited by 30
  36. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  37. 2023Neural Implicit Dense Semantic SLAMcited by 26
  38. 2024GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyondcited by 25

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 12; 2025: 22; 2026: 15.

49 papers.

Sort:

By area:

  1. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  2. 2024DiffGS: Functional Gaussian Splatting Diffusioncited by 51
  3. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  4. 2025MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstructioncited by 37
  5. 2024Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assemblycited by 35
  6. 2025FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistencycited by 31
  7. 2025MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inferencecited by 23
  8. 2024MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Viewscited by 21
  9. 2024Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-order Geometric Primitivescited by 20
  10. 2025GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstructioncited by 17
  11. 2025MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstructioncited by 15
  12. 2025GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splattingcited by 15
37 more
  1. 2025Gaussian Splatting with Discretized SDF for Relightable Assetscited by 13
  2. 2025NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstructioncited by 12
  3. 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Stepcited by 11
  4. 2024MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstructioncited by 11
  5. 2024GLS: Geometry-aware 3D Language Gaussian Splattingcited by 9
  6. 2025SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistenciescited by 9
  7. 2025VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussianscited by 8
  8. 2024GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstructioncited by 7
  9. 2024DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstructioncited by 7
  10. 2025Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generationcited by 7
  11. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  12. 2025GAP: Gaussianize Any Point Clouds with Text Guidancecited by 7
  13. 2025VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignmentcited by 6
  14. 20252D Triangle Splatting for Direct Differentiable Mesh Trainingcited by 5
  15. 2025Car-GS: Addressing Reflective and Transparent Surface Challenges in 3D Car Reconstructioncited by 4
  16. 2026UrbanGS: A Scalable and Efficient Architecture for Geometrically Accurate Large-Scene Reconstructioncited by 4
  17. 2026Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Listscited by 4
  18. 2026From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussianscited by 4
  19. 2025U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matchingcited by 3
  20. 2026Confidence-Based Mesh Extraction from 3D Gaussianscited by 3
  21. 2024Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functionscited by 2
  22. 2025Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Losscited by 1
  23. 2025From Volume Rendering to 3D Gaussian Splatting: Theory and Applicationscited by 1
  24. 2025TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splattingcited by 1
  25. 20263D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstructioncited by 1
  26. 2026SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAMcited by 1
  27. 2026VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priorscited by 1
  28. 2026Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstructioncited by 1
  29. 2025GarmentGS: Point-Cloud Guided Gaussian Splatting for High-Fidelity Non-Watertight 3D Garment Reconstructioncited by 0
  30. 2025COREA: Coupled Relightable 3D Gaussians and SDFs for Efficient Normal Alignmentcited by 0
  31. 2026SwiftNDC: Fast Neural Depth Correction for High-Fidelity 3D Reconstructioncited by 0
  32. 2026GaussFly: Contrastive Reinforcement Learning for Visuomotor Policies in 3D Gaussian Fieldscited by 0
  33. 2026Gaussian-Voxel Duet: A Dual-Scaffolding Hybrid Representation for Fast and Accurate Monocular Surface Reconstructioncited by 0
  34. 2026Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priorscited by 0
  35. 2026Incremental Online Scene Reconstruction by 3D Gaussian Triangulationcited by 0
  36. 2026Surfsvr: 2D Surface Priors as 3D Geometric Regularizers for Sparse Voxel Reconstructioncited by 0
  37. 2026Sparse-GS2Mesh: 3D Gaussian Splatting Guided by Novel Stereo Views and 2DGS for Sparse View Surface Reconstructioncited by 0