mlsanityData to 7 Oct 2026

RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds

arXiv 2204.09138 ↗First posted 19 Apr 2022cs.CV cs.AI cs.GRcited by 16

Not on the map. Why?

Abstract (arXiv)

We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds. Unlike occupancy fields or signed distance fields which can only model closed 3D surfaces, our approach is not restricted to any type of topology. Being different from the existing unsigned distance fields, our framework does not suffer from any surface ambiguity. In addition, our RangeUDF can jointly estimate precise semantics for continuous surfaces. The key to our approach is a range-aware unsigned distance function together with a surface-oriented semantic segmentation module. Extensive experiments show that RangeUDF clearly surpasses state-of-the-art approaches for surface reconstruction on four point cloud datasets. Moreover, RangeUDF demonstrates superior generalization capability across multiple unseen datasets, which is nearly impossible for all existing approaches.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 49 of its 57 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

49 of 57 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  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. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  11. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
37 more
  1. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  2. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  3. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 2020Convolutional Occupancy Networkscited by 760
  6. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  7. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  10. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  11. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  13. 2017Neural 3D Mesh Renderercited by 437
  14. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  15. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  16. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  17. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  18. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  19. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  20. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  21. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  22. 2017A Survey of Structure from Motioncited by 157
  23. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 146
  24. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  25. 2017Pointwise Convolutional Neural Networkscited by 126
  26. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  27. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  28. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  29. 20173D-PRNN: Generating Shape Primitives with Recurrent Neural Networkscited by 77
  30. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  31. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  32. 2020FroDO: From Detections to 3D Objectscited by 51
  33. 2017Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scenecited by 50
  34. 2018Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstructioncited by 44
  35. 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37
  36. 2022SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminatorscited by 26
  37. 2018Dense 3D Object Reconstruction from a Single Depth Viewcited by 24

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 7; 2024: 2; 2025: 3.

16 papers.

Sort:

  1. 2022DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Imagescited by 69
  2. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
  3. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  4. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  5. 2023NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videoscited by 28
  6. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  7. 2023RayDF: Neural Ray-surface Distance Fields with Multi-view Consistencycited by 12
  8. 2024DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scalingcited by 9
  9. 2022PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translationcited by 7
  10. 2025NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serializationcited by 3
  11. 2023Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularizationcited by 2
  12. 2024MergeNet: Explicit Mesh Reconstruction from Sparse Point Clouds via Edge Predictioncited by 2
4 more
  1. 2025RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussianscited by 1
  2. 2022TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learningcited by 0
  3. 2023Contextualising Implicit Representations for Semantic Taskscited by 0
  4. 2025Accurate and Complete Surface Reconstruction from 3D Gaussians via Direct SDF Learningcited by 0