mlsanityData to 7 Oct 2026

Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes

arXiv 2403.01414 ↗First posted 3 Mar 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Neural implicit representation of geometric shapes has witnessed considerable advancements in recent years. However, common distance field based implicit representations, specifically signed distance field (SDF) for watertight shapes or unsigned distance field (UDF) for arbitrary shapes, routinely suffer from degradation of reconstruction accuracy when converting to explicit surface points and meshes. In this paper, we introduce a novel neural implicit representation based on unsigned orthogonal distance fields (UODFs). In UODFs, the minimal unsigned distance from any spatial point to the shape surface is defined solely in one orthogonal direction, contrasting with the multi-directional determination made by SDF and UDF. Consequently, every point in the 3D UODFs can directly access its closest surface points along three orthogonal directions. This distinctive feature leverages the accurate reconstruction of surface points without interpolation errors. We verify the effectiveness of UODFs through a range of reconstruction examples, extending from simple watertight or non-watertight shapes to complex shapes that include hollows, internal or assembling structures.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 34 of its 45 references that are in the map. First posted on arXiv 3 Mar 2024.

Builds on

34 of 45 references.

References · 34

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  9. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  10. 2020PCT: Point cloud transformercited by 730
  11. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  12. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
22 more
  1. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  2. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  3. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  4. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  5. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
  6. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 182
  7. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  8. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 120
  9. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 92
  10. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 75
  11. 2022Neural Dual Contouringcited by 71
  12. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 62
  13. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  14. 2021Deep Implicit Surface Point Prediction Networkscited by 40
  15. 2023NeUDF: Leaning Neural Unsigned Distance Fields with Volume Renderingcited by 40
  16. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  17. 20223PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologiescited by 27
  18. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25
  19. 2021Representing 3D Shapes with Probabilistic Directed Distance Fieldscited by 21
  20. 2021DeepCurrents: Learning Implicit Representations of Shapes with Boundariescited by 12
  21. 2022Neural Density-Distance Fieldscited by 9
  22. 2022NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representationcited by 7

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 3.

6 papers.

  1. 2024A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functionscited by 7
  2. 2024CoFie: Learning Compact Neural Surface Representations with Coordinate Fieldscited by 5
  3. 2024Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Cloudscited by 5
  4. 2025Blind Video Super-Resolution based on Implicit Kernelscited by 4
  5. 2025OffsetOPT: Explicit Surface Reconstruction without Normalscited by 2
  6. 2025Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priorscited by 0