mlsanityData to 14 Oct 2026

Deep Implicit Moving Least-Squares Functions for 3D Reconstruction

arXiv 2103.12266 ↗First posted 23 Mar 2021cs.CV cs.GRcited by 67

Not on the map. Why?

Abstract (arXiv)

Point set is a flexible and lightweight representation widely used for 3D deep learning. However, their discrete nature prevents them from representing continuous and fine geometry, posing a major issue for learning-based shape generation. In this work, we turn the discrete point sets into smooth surfaces by introducing the well-known implicit moving least-squares (IMLS) surface formulation, which naturally defines locally implicit functions on point sets. We incorporate IMLS surface generation into deep neural networks for inheriting both the flexibility of point sets and the high quality of implicit surfaces. Our IMLSNet predicts an octree structure as a scaffold for generating MLS points where needed and characterizes shape geometry with learned local priors. Furthermore, our implicit function evaluation is independent of the neural network once the MLS points are predicted, thus enabling fast runtime evaluation. Our experiments on 3D object reconstruction demonstrate that IMLSNets outperform state-of-the-art learning-based methods in terms of reconstruction quality and computational efficiency. Extensive ablation tests also validate our network design and loss functions.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Builds on 37 of its 60 references that are in the map. First posted on arXiv 23 Mar 2021.

Builds on

37 of 60 references.

References · 37

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  9. 2020Convolutional Occupancy Networkscited by 761
  10. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  11. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  12. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
25 more
  1. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  2. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  3. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  4. 2017Neural 3D Mesh Renderercited by 437
  5. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  6. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  7. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  8. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  9. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  10. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 260
  11. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  12. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  13. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  14. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  15. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  16. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  17. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  18. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  19. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  20. 20173D-PRNN: Generating Shape Primitives with Recurrent Neural Networkscited by 77
  21. 2018PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Imagecited by 77
  22. 2020Curriculum DeepSDFcited by 62
  23. 2018Im2Struct: Recovering 3D Shape Structure from a Single RGB Imagecited by 55
  24. 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37
  25. 2020Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completioncited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 20; 2023: 18; 2024: 17; 2025: 4; 2026: 2.

67 papers.

Sort:

  1. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  2. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  3. 2023Neural Kernel Surface Reconstructioncited by 104
  4. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  5. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  6. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  7. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  8. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  9. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  10. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 47
  11. 2022Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Cloudscited by 42
  12. 2022Surface Reconstruction from Point Clouds: A Survey and a Benchmarkcited by 41
38 more
  1. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  2. 2024Improved Implicit Neural Representation with Fourier Reparameterized Trainingcited by 36
  3. 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 29
  4. 2023Unsupervised Inference of Signed Distance Functions from Single Sparse Point Clouds without Learning Priorscited by 28
  5. 2023Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulationcited by 27
  6. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  7. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25
  8. 2022Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Spacecited by 22
  9. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  10. 2022Latent Partition Implicit with Surface Codes for 3D Representationcited by 21
  11. 2023VisCo Grids: Surface Reconstruction with Viscosity and Coarea Gridscited by 20
  12. 2024Unsupervised Occupancy Learning from Sparse Point Cloudcited by 15
  13. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  14. 2021Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstructioncited by 13
  15. 2021DeepCurrents: Learning Implicit Representations of Shapes with Boundariescited by 12
  16. 2023Mixing-Denoising Generalizable Occupancy Networkscited by 12
  17. 2024PoNQ: a Neural QEM-based Mesh Representationcited by 12
  18. 2022Laplacian2Mesh: Laplacian-Based Mesh Understandingcited by 11
  19. 2022PCDNF: Revisiting Learning-based Point Cloud Denoising via Joint Normal Filteringcited by 11
  20. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  21. 2023Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priorscited by 11
  22. 2023Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Modelcited by 10
  23. 2022What's the Situation with Intelligent Mesh Generation: A Survey and Perspectivescited by 9
  24. 2024DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scalingcited by 9
  25. 2022HRBF-Fusion: Accurate 3D reconstruction from RGB-D data using on-the-fly implicitscited by 8
  26. 2022Semi-signed prioritized neural fitting for surface reconstruction from unoriented point cloudscited by 8
  27. 2024DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstructioncited by 8
  28. 2024A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functionscited by 7
  29. 2024Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Cloudscited by 7
  30. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
  31. 2024GSurf: Learning Signed Distance Fields from Splatting Opaque Gaussians for High-quality 3D Reconstructioncited by 7
  32. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  33. 2023SuperUDF: Self-supervised UDF Estimation for Surface Reconstructioncited by 6
  34. 2024Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Cloudscited by 6
  35. 2021HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulationcited by 5
  36. 2021Learning Body-Aware 3D Shape Generative Modelscited by 5
  37. 2023Coordinate Quantized Neural Implicit Representations for Multi-view Reconstructioncited by 5
  38. 2024DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fieldscited by 5

50 most cited of 67 All 67 (JSON)