mlsanityData to 7 Oct 2026

Isomorphic mesh generation from point clouds with multilayer perceptrons

arXiv 2210.14157 ↗First posted 21 Oct 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose a new neural network, called isomorphic mesh generator (iMG), which generates isomorphic meshes from point clouds containing noise and missing parts. Isomorphic meshes of arbitrary objects have a unified mesh structure even though the objects belong to different classes. This unified representation enables surface models to be handled by DNNs. Moreover, the unified mesh structure of isomorphic meshes enables the same process to be applied to all isomorphic meshes; although in the case of general mesh models, we need to consider the processes depending on their mesh structures. Therefore, the use of isomorphic meshes leads to efficient memory usage and calculation time compared with general mesh models. As iMG is a data-free method, preparing any point clouds as training data in advance is unnecessary, except a point cloud of the target object used as the input data of iMG. Additionally, iMG outputs an isomorphic mesh obtained by mapping a reference mesh to a given input point cloud. To estimate the mapping function stably, we introduce a step-by-step mapping strategy. This strategy achieves a flexible deformation while maintaining the structure of the reference mesh. From simulation and experiments using a mobile phone, we confirmed that iMG can generate isomorphic meshes of given objects reliably even when the input point cloud includes noise and missing parts.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 44 of its 79 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

44 of 79 references.

References · 44

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2020Convolutional Occupancy Networkscited by 760
  8. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  9. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  10. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  11. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  12. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
32 more
  1. 2021Neural RGB-D Surface Reconstructioncited by 312
  2. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  3. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  4. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  5. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  6. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  7. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 146
  8. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 145
  9. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  10. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  11. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  12. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  13. 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
  14. 2020Curriculum DeepSDFcited by 62
  15. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
  16. 2020Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classificationcited by 57
  17. 2019Voxel2Mesh: 3D Mesh Model Generation from Volumetric Datacited by 52
  18. 2020Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networkscited by 52
  19. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  20. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45
  21. 2019PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentationcited by 44
  22. 2020Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidancecited by 39
  23. 2019SSRNet: Scalable 3D Surface Reconstruction Networkcited by 35
  24. 2020PointTriNet: Learned Triangulation of 3D Point Setscited by 32
  25. 2020Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentionscited by 30
  26. 2020Learning Delaunay Surface Elements for Mesh Reconstructioncited by 23
  27. 2020Deep Optimized Priors for 3D Shape Modeling and Reconstructioncited by 20
  28. 2019LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Cloudscited by 14
  29. 2021Learning Fine-Grained Segmentation of 3D Shapes without Part Labelscited by 14
  30. 20213D Shapes Local Geometry Codes Learning with SDFcited by 10
  31. 2020Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshescited by 8
  32. 2018A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape Collectionscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Point Cloud to Mesh Reconstruction: Methods, Trade-offs, and Implementation Guidecited by 0