mlsanityData to 14 Oct 2026

NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation

arXiv 2206.05837 ↗First posted 12 Jun 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for different tasks thus making the transformation of one representation into another (forward map) an important and common problem. We propose Omnidirectional Distance Fields (ODFs), a new 3D shape representation that encodes geometry by storing the depth to the object's surface from any 3D position in any viewing direction. Since rays are the fundamental unit of an ODF, it can be used to easily transform to and from common 3D representations like meshes or point clouds. Different from level set methods that are limited to representing closed surfaces, ODFs are unsigned and can thus model open surfaces (e.g., garments). We demonstrate that ODFs can be effectively learned with a neural network (NeuralODF) despite the inherent discontinuities at occlusion boundaries. We also introduce efficient forward mapping algorithms for transforming ODFs to and from common 3D representations. Specifically, we introduce an efficient Jumping Cubes algorithm for generating meshes from ODFs. Experiments demonstrate that NeuralODF can learn to capture high-quality shape by overfitting to a single object, and also learn to generalize on common shape categories.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 38 of its 59 references that are in the map. First posted on arXiv 12 Jun 2022.

Builds on

38 of 59 references.

References · 38

  1. 2016Layer Normalizationcited by 5,669
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  9. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  10. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  11. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  12. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
26 more
  1. 2020Convolutional Occupancy Networkscited by 761
  2. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  4. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  5. 2021Neural Fields in Visual Computing and Beyondcited by 540
  6. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  7. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  8. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  9. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  10. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  11. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  12. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  13. 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
  14. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  15. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  16. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  17. 2018Point Cloud GANcited by 79
  18. 2016Unsupervised Learning of 3D Structure from Imagescited by 67
  19. 2020Curriculum DeepSDFcited by 62
  20. 2018Scan2Mesh: From Unstructured Range Scans to 3D Meshescited by 51
  21. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  22. 2020CNNs on Surfaces using Rotation-Equivariant Featurescited by 43
  23. 2020Pix2Surf: Learning Parametric 3D Surface Models of Objects from Imagescited by 22
  24. 2021Representing 3D Shapes with Probabilistic Directed Distance Fieldscited by 21
  25. 2020Continuous Geodesic Convolutions for Learning on 3D Shapescited by 14
  26. 2019PointWise: An Unsupervised Point-wise Feature Learning Networkcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 1.

7 papers.

  1. 2023DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Fieldcited by 17
  2. 2024Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapescited by 6
  3. 2023Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representationscited by 5
  4. 2022OmniNeRF: Hybriding Omnidirectional Distance and Radiance fields for Neural Surface Reconstructioncited by 2
  5. 2024Efficient Visibility Approximation for Game AI using Neural Omnidirectional Distance Fieldscited by 1
  6. 2024Probabilistic Directed Distance Fields for Ray-Based Shape Representationscited by 0
  7. 2025Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residualscited by 0