mlsanityData to 14 Oct 2026

NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies

arXiv 2211.14173 ↗First posted 25 Nov 2022cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. Recent advances in neural rendering based reconstruction have achieved compelling results. However, these methods are limited to objects with closed surfaces since they adopt Signed Distance Function (SDF) as surface representation which requires the target shape to be divided into inside and outside. In this paper, we propose to represent surfaces as the Unsigned Distance Function (UDF) and develop a new volume rendering scheme to learn the neural UDF representation. Specifically, a new density function that correlates the property of UDF with the volume rendering scheme is introduced for robust optimization of the UDF fields. Experiments on the DTU and DeepFashion3D datasets show that our method not only enables high-quality reconstruction of non-closed shapes with complex typologies, but also achieves comparable performance to the SDF based methods on the reconstruction of closed surfaces.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 25 Nov 2022.

Builds on

36 of 58 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  6. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  11. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  12. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
24 more
  1. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  2. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  3. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  4. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  5. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  6. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  7. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  8. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
  9. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  10. 2017Learning a Multi-View Stereo Machinecited by 194
  11. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 180
  12. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
  13. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  14. 2021Improving neural implicit surfaces geometry with patch warpingcited by 137
  15. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  16. 2021Neural Lumigraph Renderingcited by 105
  17. 2020Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Imagescited by 103
  18. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  19. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 76
  20. 2020Multi-view Depth Estimation using Epipolar Spatio-Temporal Networkscited by 59
  21. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
  22. 2020Occlusion-Aware Depth Estimation with Adaptive Normal Constraintscited by 41
  23. 20223PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologiescited by 27
  24. 2020SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view Stereopsiscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 17; 2024: 27; 2025: 12; 2026: 7.

63 papers.

Sort:

By area:

  1. 2023Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinementcited by 106
  2. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 79
  3. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 49
  4. 2024DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shadingcited by 41
  5. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  6. 2023Single-view 3D Scene Reconstruction with High-fidelity Shape and Texturecited by 37
  7. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  8. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 33
  9. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  10. 2023Ghost on the Shell: An Expressive Representation of General 3D Shapescited by 24
  11. 2024UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusioncited by 23
  12. 2023Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Coveringcited by 22
38 more
  1. 2024VRP-UDF: Towards Unbiased Learning of Unsigned Distance Functions from Multi-view Images with Volume Rendering Priorscited by 17
  2. 2024Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fieldscited by 16
  3. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  4. 2025GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splattingcited by 15
  5. 2024Geometry Field Splatting with Gaussian Surfelscited by 13
  6. 20243D Neural Edge Reconstructioncited by 12
  7. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  8. 2023Digging into Depth Priors for Outdoor Neural Radiance Fieldscited by 11
  9. 2023CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learningcited by 11
  10. 2024DMesh++: An Efficient Differentiable Mesh for Complex Shapescited by 11
  11. 2023NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstructioncited by 10
  12. 2023NeTO:Neural Reconstruction of Transparent Objects with Self-Occlusion Aware Refraction-Tracingcited by 9
  13. 2024DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scalingcited by 9
  14. 2024Neural-ABC: Neural Parametric Models for Articulated Body with Clothescited by 9
  15. 2024DMesh: A Differentiable Mesh Representationcited by 9
  16. 2025Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representationcited by 9
  17. 20232S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Imagescited by 8
  18. 2023Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Modelscited by 8
  19. 2025PDT: Point Distribution Transformation with Diffusion Modelscited by 8
  20. 2023NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDFcited by 7
  21. 2024Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstructioncited by 7
  22. 2024A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functionscited by 7
  23. 2024Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapescited by 6
  24. 2023Sketch2Cloth: Sketch-based 3D Garment Generation with Unsigned Distance Fieldscited by 5
  25. 20244DRecons: 4D Neural Implicit Deformable Objects Reconstruction from a single RGB-D Camera with Geometrical and Topological Regularizationscited by 5
  26. 2024HashPoint: Accelerated Point Searching and Sampling for Neural Renderingcited by 4
  27. 2024Depth Reconstruction with Neural Signed Distance Fields in Structured Light Systemscited by 4
  28. 2024DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fieldscited by 4
  29. 2025Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstructioncited by 4
  30. 2025NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serializationcited by 3
  31. 2025HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguitycited by 3
  32. 2024Oriented-grid Encoder for 3D Implicit Representationscited by 2
  33. 2024From Transparent to Opaque: Rethinking Neural Implicit Surfaces with α-NeuScited by 2
  34. 20243D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapescited by 2
  35. 2025High Resolution UDF Meshing via Iterative Networkscited by 2
  36. 2024High-fidelity Endoscopic Image Synthesis by Utilizing Depth-guided Neural Surfacescited by 1
  37. 2024Point Cloud Unsupervised Pre-training via 3D Gaussian Splattingcited by 1
  38. 20263D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstructioncited by 1

50 most cited of 63 All 63 (JSON)