mlsanityData to 7 Oct 2026

Graph-Guided Deformation for Point Cloud Completion

arXiv 2112.01840 ↗First posted 11 Nov 2021cs.RO cs.AI cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

For a long time, the point cloud completion task has been regarded as a pure generation task. After obtaining the global shape code through the encoder, a complete point cloud is generated using the shape priorly learnt by the networks. However, such models are undesirably biased towards prior average objects and inherently limited to fit geometry details. In this paper, we propose a Graph-Guided Deformation Network, which respectively regards the input data and intermediate generation as controlling and supporting points, and models the optimization guided by a graph convolutional network(GCN) for the point cloud completion task. Our key insight is to simulate the least square Laplacian deformation process via mesh deformation methods, which brings adaptivity for modeling variation in geometry details. By this means, we also reduce the gap between the completion task and the mesh deformation algorithms. As far as we know, we are the first to refine the point cloud completion task by mimicing traditional graphics algorithms with GCN-guided deformation. We have conducted extensive experiments on both the simulated indoor dataset ShapeNet, outdoor dataset KITTI, and our self-collected autonomous driving dataset Pandar40. The results show that our method outperforms the existing state-of-the-art algorithms in the 3D point cloud completion task.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 11 Nov 2021.

Builds on

27 of 43 references.

References · 27

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  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. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  8. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  9. 2018PCN: Point Completion Networkcited by 382
  10. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  11. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  12. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
15 more
  1. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  2. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  3. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  4. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  5. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  6. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  7. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  8. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  9. 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 84
  10. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  11. 2020Skeleton-bridged Point Completion: From Global Inference to Local Adjustmentcited by 23
  12. 20203D Reconstruction of Novel Object Shapes from Single Imagescited by 21
  13. 2020Interactive Annotation of 3D Object Geometry using 2D Scribblescited by 13
  14. 2018P2P-NET: Bidirectional Point Displacement Net for Shape Transformcited by 11
  15. 2019DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfacescited by 9

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3.

6 papers.

  1. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  2. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  3. 2023Dynamic Point Fieldscited by 37
  4. 2022Temporal Point Cloud Completion with Pose Disturbancecited by 5
  5. 2023What You See Is What You Detect: Towards better Object Densification in 3D detectioncited by 1
  6. 2023Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completioncited by 0