mlsanityData to 14 Oct 2026

Neural Dual Contouring

arXiv 2202.01999 ↗First posted 4 Feb 2022cs.CV cs.GR cs.LGcited by 71

Not on the map. Why?

Abstract (arXiv)

We introduce neural dual contouring (NDC), a new data-driven approach to mesh reconstruction based on dual contouring (DC). Like traditional DC, it produces exactly one vertex per grid cell and one quad for each grid edge intersection, a natural and efficient structure for reproducing sharp features. However, rather than computing vertex locations and edge crossings with hand-crafted functions that depend directly on difficult-to-obtain surface gradients, NDC uses a neural network to predict them. As a result, NDC can be trained to produce meshes from signed or unsigned distance fields, binary voxel grids, or point clouds (with or without normals); and it can produce open surfaces in cases where the input represents a sheet or partial surface. During experiments with five prominent datasets, we find that NDC, when trained on one of the datasets, generalizes well to the others. Furthermore, NDC provides better surface reconstruction accuracy, feature preservation, output complexity, triangle quality, and inference time in comparison to previous learned (e.g., neural marching cubes, convolutional occupancy networks) and traditional (e.g., Poisson) methods. Code and data are available at https://github.com/czq142857/NDC.

Key facts. Cited by 71 papers in the map (data through 14 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

32 of 56 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  9. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  10. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  11. 2020Convolutional Occupancy Networkscited by 761
  12. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
20 more
  1. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  2. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
  3. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  4. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  5. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  6. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  7. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 245
  8. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  9. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 183
  10. 2020MeshSDF: Differentiable Iso-Surface Extractioncited by 112
  11. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  12. 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 85
  13. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  14. 2021Neural Marching Cubescited by 50
  15. 2020Point2Mesh: A Self-Prior for Deformable Meshescited by 41
  16. 2020Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidancecited by 39
  17. 2019SSRNet: Scalable 3D Surface Reconstruction Networkcited by 35
  18. 2020PointTriNet: Learned Triangulation of 3D Point Setscited by 32
  19. 2020Meshlet Priors for 3D Mesh Reconstructioncited by 23
  20. 2020Learning Delaunay Surface Elements for Mesh Reconstructioncited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 16; 2024: 21; 2025: 19; 2026: 10.

71 papers.

Sort:

By area:

  1. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
  2. 2025Native and Compact Structured Latents for 3D Generationcited by 175
  3. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 144
  4. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 139
  5. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 79
  6. 2023Controllable Mesh Generation Through Sparse Latent Point Diffusion Modelscited by 41
  7. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 33
  8. 2023NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Supportcited by 25
  9. 2023Ghost on the Shell: An Expressive Representation of General 3D Shapescited by 24
  10. 2023NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloudcited by 22
  11. 2023Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Coveringcited by 22
  12. 2024Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenescited by 22
38 more
  1. 2024SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshescited by 20
  2. 2024Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioningcited by 18
  3. 2025GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splattingcited by 15
  4. 2024PoNQ: a Neural QEM-based Mesh Representationcited by 12
  5. 2024NeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvaturecited by 12
  6. 2023A Survey and Benchmark of Automatic Surface Reconstruction from Point Cloudscited by 11
  7. 2024DMesh++: An Efficient Differentiable Mesh for Complex Shapescited by 11
  8. 2022What's the Situation with Intelligent Mesh Generation: A Survey and Perspectivescited by 9
  9. 2024DMesh: A Differentiable Mesh Representationcited by 9
  10. 2024DECOLLAGE: 3D Detailization by Controllable, Localized, and Learned Geometry Enhancementcited by 7
  11. 2026MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformercited by 7
  12. 2023NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Renderingcited by 6
  13. 2024Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapescited by 6
  14. 2025TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimizationcited by 6
  15. 2026FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generationcited by 6
  16. 2022Neural Volumetric Mesh Generatorcited by 5
  17. 2023Interaction-Driven Active 3D Reconstruction with Object Interiorscited by 5
  18. 2024Design2Cloth: 3D Cloth Generation from 2D Maskscited by 5
  19. 2025Point2Quad: Generating Quad Meshes from Point Clouds via Face Predictioncited by 5
  20. 2025From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Imagescited by 5
  21. 2022Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representationcited by 4
  22. 2023Adaptive Local Basis Functions for Shape Completioncited by 4
  23. 2024Neural Surface Detection for Unsigned Distance Fieldscited by 4
  24. 2024DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fieldscited by 4
  25. 2024McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extractioncited by 4
  26. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  27. 2023Text-guided Image-and-Shape Editing and Generation: A Short Surveycited by 3
  28. 2023PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstructioncited by 3
  29. 2024PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstructioncited by 3
  30. 2024Occupancy-Based Dual Contouringcited by 3
  31. 2024Neurally Integrated Finite Elements for Differentiable Elasticity on Evolving Domainscited by 3
  32. 2025Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapescited by 3
  33. 2025A Survey of AI Methods for Geometry Preparation and Mesh Generation in Engineering Simulationcited by 3
  34. 2022ARO-Net: Learning Implicit Fields from Anchored Radial Observationscited by 2
  35. 2023CircNet: Meshing 3D Point Clouds with Circumcenter Detectioncited by 2
  36. 2024Self-Supervised Dual Contouringcited by 2
  37. 2025SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generationcited by 2
  38. 2025OffsetOPT: Explicit Surface Reconstruction without Normalscited by 2

50 most cited of 71 All 71 (JSON)