mlsanityData to 14 Oct 2026

Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priors

arXiv 2303.14505 ↗First posted 25 Mar 2023cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

It is vital to infer signed distance functions (SDFs) from 3D point clouds. The latest methods rely on generalizing the priors learned from large scale supervision. However, the learned priors do not generalize well to various geometric variations that are unseen during training, especially for extremely sparse point clouds. To resolve this issue, we present a neural network to directly infer SDFs from single sparse point clouds without using signed distance supervision, learned priors or even normals. Our insight here is to learn surface parameterization and SDFs inference in an end-to-end manner. To make up the sparsity, we leverage parameterized surfaces as a coarse surface sampler to provide many coarse surface estimations in training iterations, according to which we mine supervision and our thin plate splines (TPS) based network infers SDFs as smooth functions in a statistical way. Our method significantly improves the generalization ability and accuracy in unseen point clouds. Our experimental results show our advantages over the state-of-the-art methods in surface reconstruction for sparse point clouds under synthetic datasets and real scans.The code is available at urlhttps://github.com/chenchao15/NeuralTPS.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 70 of its 92 references that are in the map. First posted on arXiv 25 Mar 2023.

Builds on

70 of 92 references.

References · 70

  1. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  8. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  9. 2020Convolutional Occupancy Networkscited by 761
  10. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  11. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  12. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
38 more
  1. 2019Neural Spline Flowscited by 596
  2. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  3. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  4. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  5. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  6. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  7. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  8. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  9. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  10. 2020Learning Gradient Fields for Shape Generationcited by 245
  11. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  12. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  13. 2022Thin-Plate Spline Motion Model for Image Animationcited by 210
  14. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  15. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 180
  16. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  17. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  18. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  19. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  20. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  21. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 121
  22. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  23. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  24. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  25. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  26. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  27. 2020PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representationscited by 81
  28. 2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 77
  29. 2019Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priorscited by 74
  30. 2020SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Imagescited by 68
  31. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  32. 2021ACORN: Adaptive Coordinate Networks for Neural Scene Representationcited by 65
  33. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 63
  34. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  35. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  36. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  37. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  38. 2019Deep Level Sets: Implicit Surface Representations for 3D Shape Inferencecited by 53

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 11; 2025: 5; 2026: 1.

28 papers.

Sort:

  1. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 49
  2. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  3. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  4. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  5. 2023Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsamplingcited by 19
  6. 2024SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearizationcited by 19
  7. 2024Unsupervised Occupancy Learning from Sparse Point Cloudcited by 15
  8. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  9. 2023Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priorscited by 11
  10. 2023NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Functioncited by 10
  11. 2025Sparfels: Fast Reconstruction from Sparse Unposed Imagerycited by 8
  12. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
16 more
  1. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  2. 2025SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splattingcited by 7
  3. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  4. 2024FSC: Few-point Shape Completioncited by 6
  5. 2023Coordinate Quantized Neural Implicit Representations for Multi-view Reconstructioncited by 5
  6. 2024Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversariescited by 5
  7. 2024Toward Robust Neural Reconstruction from Sparse Point Setscited by 5
  8. 2024PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstructioncited by 3
  9. 2024Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classescited by 3
  10. 2023Learning Self-Prior for Mesh Inpainting Using Self-Supervised Graph Convolutional Networkscited by 2
  11. 2024MergeNet: Explicit Mesh Reconstruction from Sparse Point Clouds via Edge Predictioncited by 2
  12. 2024Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functionscited by 2
  13. 2025Low-Rank Tensor Recovery via Variational Schatten-p Quasi-Norm and Jacobian Regularizationcited by 1
  14. 2026SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAMcited by 1
  15. 2023Polyhedral Surface: Self-supervised Point Cloud Reconstruction Based on Polyhedral Surfacecited by 0
  16. 2025Learning to Upscale 3D Segmentations in Neuroimagingcited by 0