mlsanityData to 7 Oct 2026

PF-Net: Point Fractal Network for 3D Point Cloud Completion

arXiv 2003.00410 ↗First posted 1 Mar 2020cs.CV cs.GRcited by 146

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a Point Fractal Network (PF-Net), a novel learning-based approach for precise and high-fidelity point cloud completion. Unlike existing point cloud completion networks, which generate the overall shape of the point cloud from the incomplete point cloud and always change existing points and encounter noise and geometrical loss, PF-Net preserves the spatial arrangements of the incomplete point cloud and can figure out the detailed geometrical structure of the missing region(s) in the prediction. To succeed at this task, PF-Net estimates the missing point cloud hierarchically by utilizing a feature-points-based multi-scale generating network. Further, we add up multi-stage completion loss and adversarial loss to generate more realistic missing region(s). The adversarial loss can better tackle multiple modes in the prediction. Our experiments demonstrate the effectiveness of our method for several challenging point cloud completion tasks.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 33; 2023: 22; 2024: 22; 2025: 21; 2026: 14.

146 papers.

Sort:

By area:

  1. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  2. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  3. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
  4. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  5. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  6. 20213D Semantic Scene Completion: a Surveycited by 74
  7. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  8. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  9. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 65
  10. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  11. 2021Semantic Scene Completion via Integrating Instances and Scene in-the-Loopcited by 54
  12. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
38 more
  1. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  2. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  3. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  4. 2021Style-based Point Generator with Adversarial Rendering for Point Cloud Completioncited by 45
  5. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  6. 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 43
  7. 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
  8. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  9. 2022Cross-modal Learning for Image-Guided Point Cloud Shape Completioncited by 36
  10. 2023SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generatorcited by 34
  11. 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
  12. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  13. 2021ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completioncited by 28
  14. 2021MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancycited by 27
  15. 2025DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundnesscited by 24
  16. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  17. 2024CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformerscited by 21
  18. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  19. 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorizationcited by 20
  20. 2021ME-PCN: Point Completion Conditioned on Mask Emptinesscited by 18
  21. 2021Denoise and Contrast for Category Agnostic Shape Completioncited by 17
  22. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17
  23. 2022Learning a Structured Latent Space for Unsupervised Point Cloud Completioncited by 17
  24. 2022Revealing Occlusions with 4D Neural Fieldscited by 17
  25. 2021Self-Supervised Point Cloud Completion via Inpaintingcited by 16
  26. 2024PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priorscited by 16
  27. 2021Point Cloud Learning with Transformercited by 15
  28. 2021Deep Point Cloud Reconstructioncited by 15
  29. 2025SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidancecited by 15
  30. 2021FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registrationcited by 14
  31. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  32. 2021SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloudcited by 12
  33. 2021Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learningcited by 12
  34. 2023U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Cloudscited by 11
  35. 2022PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognitioncited by 10
  36. 2022CAB: Comprehensive Attention Benchmarking on Long Sequence Modelingcited by 10
  37. 2021KTNet: Knowledge Transfer for Unpaired 3D Shape Completioncited by 9
  38. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9

50 most cited of 146 All 146 (JSON)