mlsanityData to 14 Oct 2026

MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step

arXiv 2411.01208 ↗First posted 2 Nov 2024cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Reconstructing a continuous surface from a raw 3D point cloud is a challenging task. Recent methods usually train neural networks to overfit on single point clouds to infer signed distance functions (SDFs). However, neural networks tend to smooth local details due to the lack of ground truth signed distances or normals, which limits the performance of overfitting-based methods in reconstruction tasks. To resolve this issue, we propose a novel method, named MultiPull, to learn multi-scale implicit fields from raw point clouds by optimizing accurate SDFs from coarse to fine. We achieve this by mapping 3D query points into a set of frequency features, which makes it possible to leverage multi-level features during optimization. Meanwhile, we introduce optimization constraints from the perspective of spatial distance and normal consistency, which play a key role in point cloud reconstruction based on multi-scale optimization strategies. Our experiments on widely used object and scene benchmarks demonstrate that our method outperforms the state-of-the-art methods in surface reconstruction.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 49 of its 71 references that are in the map. First posted on arXiv 2 Nov 2024.

Builds on

49 of 71 references.

References · 49

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  4. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  5. 2020Convolutional Occupancy Networkscited by 761
  6. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  7. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  9. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  10. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  11. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  12. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
37 more
  1. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  2. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  3. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  4. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 183
  5. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  6. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  7. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  8. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  9. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  10. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  11. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  12. 2020Curriculum DeepSDFcited by 62
  13. 2022Improved Direct Voxel Grid Optimization for Radiance Fields Reconstructioncited by 61
  14. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  15. 2022Vox-Surf: Voxel-based Implicit Surface Representationcited by 49
  16. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 49
  17. 2023NeUDF: Leaning Neural Unsigned Distance Fields with Volume Renderingcited by 41
  18. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  19. 2020Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidancecited by 39
  20. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  21. 2022NeAF: Learning Neural Angle Fields for Point Normal Estimationcited by 38
  22. 2023Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Fieldcited by 37
  23. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  24. 2019SSRNet: Scalable 3D Surface Reconstruction Networkcited by 35
  25. 2020DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Imagescited by 35
  26. 2023Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessiancited by 35
  27. 2021Orienting Point Clouds with Dipole Propagationcited by 31
  28. 2022Iterative Poisson Surface Reconstruction (iPSR) for Unoriented Pointscited by 31
  29. 2020Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Cloudscited by 30
  30. 2022GenSDF: Two-Stage Learning of Generalizable Signed Distance Functionscited by 30
  31. 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 29
  32. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  33. 2021Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matchingcited by 26
  34. 2023VisCo Grids: Surface Reconstruction with Viscosity and Coarea Gridscited by 20
  35. 2016Orientation-boosted Voxel Nets for 3D Object Recognitioncited by 17
  36. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  37. 2023Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priorscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 4.

11 papers.

  1. 2025MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstructioncited by 15
  2. 2025GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splattingcited by 15
  3. 2025NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstructioncited by 12
  4. 2026MoRe: Motion-aware Feed-forward 4D Reconstruction Transformercited by 9
  5. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  6. 2025GAP: Gaussianize Any Point Clouds with Text Guidancecited by 7
  7. 2024NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Cloudscited by 2
  8. 2024Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functionscited by 2
  9. 2026SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAMcited by 1
  10. 2026GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidancecited by 1
  11. 2026AnySurf: Any Surface Generation with Directed Edgecited by 1