mlsanityData to 14 Oct 2026

GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation

arXiv 2211.16762 ↗First posted 30 Nov 2022cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

We present a learning-based method, namely GeoUDF,to tackle the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud.To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation that explicitly formulates the unsigned distance of a query point as the learnable affine averaging of its distances to the tangent planes of neighboring points on the surface. Besides,we model the local geometric structure of the input point clouds by explicitly learning a quadratic polynomial for each point. This not only facilitates upsampling the input sparse point cloud but also naturally induces unoriented normal, which further augments UDF estimation. Finally, to extract triangle meshes from the predicted UDF we propose a customized edge-based marching cube module. We conduct extensive experiments and ablation studies to demonstrate the significant advantages of our method over state-of-the-art methods in terms of reconstruction accuracy, efficiency, and generality. The source code is publicly available at https://github.com/rsy6318/GeoUDF.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

33 of 44 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  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. 2020Convolutional Occupancy Networkscited by 761
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  10. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  11. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  12. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
21 more
  1. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  2. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  3. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  4. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  5. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  6. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  7. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  8. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
  9. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  10. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 76
  11. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  12. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69
  13. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  14. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  15. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  16. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 47
  17. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  18. 2019Shape Reconstruction by Learning Differentiable Surface Representationscited by 37
  19. 2020Deep Magnification-Flexible Upsampling over 3D Point Cloudscited by 27
  20. 2022PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsamplingcited by 18
  21. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 10; 2025: 10; 2026: 6.

29 papers.

Sort:

By area:

  1. 2023Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Coveringcited by 22
  2. 2024MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Stepcited by 11
  3. 2023Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Imagescited by 8
  4. 2024DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstructioncited by 8
  5. 2024Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstructioncited by 7
  6. 2024A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functionscited by 7
  7. 2024Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learningcited by 6
  8. 2024Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Cloudscited by 6
  9. 2024DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fieldscited by 5
  10. 2024DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fieldscited by 4
  11. 2025RBFIM: Perceptual Quality Assessment for Compressed Point Clouds Using Radial Basis Function Interpolationcited by 2
  12. 2025High Resolution UDF Meshing via Iterative Networkscited by 2
17 more
  1. 2024Parameterize Structure with Differentiable Template for 3D Shape Generationcited by 1
  2. 2024Point Cloud Unsupervised Pre-training via 3D Gaussian Splattingcited by 1
  3. 2025Non-uniform Point Cloud Upsampling via Local Manifold Distributioncited by 1
  4. 2025A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds Using 0-1 Integer Optimizationcited by 1
  5. 2025Voronoi-Assisted Optimization for Diffusing Unsigned Distance Fields from Unoriented Pointscited by 1
  6. 2023Analysis of Sampling Strategies for Implicit 3D Reconstructioncited by 0
  7. 2025Separability Membrane: 3D Active Contour for Point Cloud Surface Reconstructioncited by 0
  8. 2025MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstructioncited by 0
  9. 2025Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshescited by 0
  10. 2025PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Modelscited by 0
  11. 2025T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representationcited by 0
  12. 2026Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similaritycited by 0
  13. 2026MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenescited by 0
  14. 2026Joint Orientation and Weight Optimization for Robust Watertight Surface Reconstruction via Dirichlet-Regularized Winding Fieldscited by 0
  15. 2026SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfacescited by 0
  16. 2026Projective Normal Fields: A Convex Optimization Method for Constructing Smooth UDFscited by 0
  17. 2026Volume Rendering with Metric--Phase Fields for Thin Structures and Sign-Ambiguous Geometrycited by 0