mlsanityData to 7 Oct 2026

Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors

arXiv 2410.19680 ↗First posted 25 Oct 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

It is important to estimate an accurate signed distance function (SDF) from a point cloud in many computer vision applications. The latest methods learn neural SDFs using either a data-driven based or an overfitting-based strategy. However, these two kinds of methods are with either poor generalization or slow convergence, which limits their capability under challenging scenarios like highly noisy point clouds. To resolve this issue, we propose a method to promote pros of both data-driven based and overfitting-based methods for better generalization, faster inference, and higher accuracy in learning neural SDFs. We introduce a novel statistical reasoning algorithm in local regions which is able to finetune data-driven based priors without signed distance supervision, clean point cloud, or point normals. This helps our method start with a good initialization, and converge to a minimum in a much faster way. Our numerical and visual comparisons with the state-of-the-art methods show our superiority over these methods in surface reconstruction and point cloud denoising on widely used shape and scene benchmarks. The code is available at https://github.com/chenchao15/LocalN2NM.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 85 of its 102 references that are in the map. First posted on arXiv 25 Oct 2024.

Builds on

85 of 102 references.

References · 85

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  9. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  10. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  11. 2020Convolutional Occupancy Networkscited by 760
  12. 2020Implicit Geometric Regularization for Learning Shapescited by 707
38 more
  1. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  2. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  3. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  4. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  5. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  6. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  7. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  8. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  9. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  10. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  11. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  12. 2020Learning Gradient Fields for Shape Generationcited by 245
  13. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  14. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  15. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  16. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  17. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  18. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  19. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 146
  20. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  21. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  22. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 120
  23. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  24. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  25. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  26. 2023Neural Kernel Surface Reconstructioncited by 102
  27. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  28. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  29. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  30. 2021Score-Based Point Cloud Denoisingcited by 83
  31. 2020PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representationscited by 81
  32. 2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 76
  33. 2019Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priorscited by 74
  34. 2020SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Imagescited by 68
  35. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  36. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  37. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  38. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splattingcited by 14
  2. 2025NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstructioncited by 12
  3. 2024Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functionscited by 2
  4. 2026SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAMcited by 1
  5. 2026AnySurf: Any Surface Generation with Directed Edgecited by 1
  6. 2025NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervisioncited by 0
  7. 2025Deep Learning For Point Cloud Denoising: A Surveycited by 0