mlsanityData to 7 Oct 2026

Voxel-based Network for Shape Completion by Leveraging Edge Generation

arXiv 2108.09936 ↗First posted 23 Aug 2021cs.CV cs.AIcited by 32

Not on the map. Why?

Abstract (arXiv)

Deep learning technique has yielded significant improvements in point cloud completion with the aim of completing missing object shapes from partial inputs. However, most existing methods fail to recover realistic structures due to over-smoothing of fine-grained details. In this paper, we develop a voxel-based network for point cloud completion by leveraging edge generation (VE-PCN). We first embed point clouds into regular voxel grids, and then generate complete objects with the help of the hallucinated shape edges. This decoupled architecture together with a multi-scale grid feature learning is able to generate more realistic on-surface details. We evaluate our model on the publicly available completion datasets and show that it outperforms existing state-of-the-art approaches quantitatively and qualitatively. Our source code is available at https://github.com/xiaogangw/VE-PCN.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 43 of its 51 references that are in the map. First posted on arXiv 23 Aug 2021.

Builds on

43 of 51 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  11. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  12. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
31 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  2. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  3. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  4. 2018PCN: Point Completion Networkcited by 382
  5. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  6. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  7. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  8. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  9. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  10. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  11. 2019EdgeConnect: Generative Image Inpainting with Adversarial Edge Learningcited by 161
  12. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  13. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  14. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  15. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  16. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  17. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  18. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  19. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  20. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  21. 20193DN: 3D Deformation Networkcited by 60
  22. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  23. 2020SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classificationcited by 33
  24. 2020Weakly-supervised 3D Shape Completion in the Wildcited by 33
  25. 2017Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networkscited by 23
  26. 2020Skeleton-bridged Point Completion: From Global Inference to Local Adjustmentcited by 23
  27. 2020Point Set Voting for Partial Point Cloud Analysiscited by 22
  28. 2018Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Weldingcited by 14
  29. 2020Point Cloud Completion by Learning Shape Priorscited by 14
  30. 2019A Convolutional Decoder for Point Clouds using Adaptive Instance Normalizationcited by 8
  31. 2020KAPLAN: A 3D Point Descriptor for Shape Completioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 7; 2024: 11; 2025: 3; 2026: 1.

32 papers.

Sort:

By area:

  1. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  2. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  3. 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 43
  4. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  5. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  6. 2023ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Modelcited by 38
  7. 2023SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generatorcited by 34
  8. 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Visioncited by 31
  9. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  10. 2025SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidancecited by 15
  11. 2023MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Drivingcited by 11
  12. 2021KTNet: Knowledge Transfer for Unpaired 3D Shape Completioncited by 9
20 more
  1. 2025PointSea: Point Cloud Completion via Self-structure Augmentationcited by 9
  2. 2022PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformationcited by 7
  3. 2024GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformercited by 7
  4. 2022SoftPool++: An Encoder-Decoder Network for Point Cloud Completioncited by 6
  5. 2024FSC: Few-point Shape Completioncited by 6
  6. 2024Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generationcited by 6
  7. 2024Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learningcited by 5
  8. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  9. 2023Learning Effective NeRFs and SDFs Representations with 3D Generative Adversarial Networks for 3D Object Generationcited by 3
  10. 2022Point cloud completion via structured feature maps using a feedback networkcited by 2
  11. 2022SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generationcited by 2
  12. 2024PillarGen: Enhancing Radar Point Cloud Density and Quality via Pillar-based Point Generation Networkcited by 2
  13. 2024You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objectscited by 2
  14. 2024DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completioncited by 2
  15. 2024FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidancecited by 1
  16. 2024Enhancing Performance of Point Cloud Completion Networks with Consistency Losscited by 1
  17. 2024Curvature Informed Furthest Point Samplingcited by 1
  18. 2023Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completioncited by 0
  19. 2025RL-AD-Net: Reinforcement Learning Guided Adaptive Displacement in Latent Space for Refined Point Cloud Completioncited by 0
  20. 2026SUMI: Scalable Unified Model for 3D Point Cloud Inferencecited by 0