mlsanityData to 7 Oct 2026

PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks

arXiv 1912.03264 ↗First posted 30 Nov 2019cs.CV cs.CG cs.LGcited by 100

Not on the map. Why?

Abstract (arXiv)

The effectiveness of learning-based point cloud upsampling pipelines heavily relies on the upsampling modules and feature extractors used therein. For the point upsampling module, we propose a novel model called NodeShuffle, which uses a Graph Convolutional Network (GCN) to better encode local point information from point neighborhoods. NodeShuffle is versatile and can be incorporated into any point cloud upsampling pipeline. Extensive experiments show how NodeShuffle consistently improves state-of-the-art upsampling methods. For feature extraction, we also propose a new multi-scale point feature extractor, called Inception DenseGCN. By aggregating features at multiple scales, this feature extractor enables further performance gain in the final upsampled point clouds. We combine Inception DenseGCN with NodeShuffle into a new point upsampling pipeline called PU-GCN. PU-GCN sets new state-of-art performance with much fewer parameters and more efficient inference.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 27; 2023: 19; 2024: 17; 2025: 20; 2026: 6.

100 papers.

Sort:

By area:

  1. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  2. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  3. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  4. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 51
  5. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  6. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  7. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
  8. 2022Density-preserving Deep Point Cloud Compressioncited by 39
  9. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  10. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  11. 2021ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learningcited by 29
  12. 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 28
38 more
  1. 2023A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsamplingcited by 28
  2. 2021MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancycited by 27
  3. 2022Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representationcited by 24
  4. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  5. 2024CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformerscited by 21
  6. 2022FBNet: Feedback Network for Point Cloud Completioncited by 20
  7. 2023Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsamplingcited by 19
  8. 2022PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsamplingcited by 18
  9. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17
  10. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  11. 2023Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-trainingcited by 17
  12. 2022PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsamplingcited by 16
  13. 2024LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernelscited by 15
  14. 2022Point Cloud Upsampling via Cascaded Refinement Networkcited by 14
  15. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  16. 2021PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsamplingcited by 11
  17. 2023Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learningcited by 10
  18. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  19. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 9
  20. 2023Lidar Upsampling with Sliced Wasserstein Distancecited by 8
  21. 2022Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Predictioncited by 7
  22. 2024GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformercited by 7
  23. 2024GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsamplingcited by 7
  24. 2021GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processingcited by 6
  25. 2022Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussianscited by 6
  26. 2022Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understandingcited by 6
  27. 2021Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Imagecited by 5
  28. 2022Upsampling Autoencoder for Self-Supervised Point Cloud Learningcited by 4
  29. 2022Physics and semantic informed multi-sensor calibration via optimization theory and self-supervised learningcited by 4
  30. 2023DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstructioncited by 4
  31. 2023Novel class discovery meets foundation models for 3D semantic segmentationcited by 4
  32. 2024Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinementcited by 4
  33. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  34. 2025Efficient Point Clouds Upsampling via Flow Matchingcited by 4
  35. 2025Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentationcited by 4
  36. 2021"Zero-Shot" Point Cloud Upsamplingcited by 3
  37. 2023Arbitrary point cloud upsampling via Dual Back-Projection Networkcited by 3
  38. 2022Point cloud completion via structured feature maps using a feedback networkcited by 2

50 most cited of 100 All 100 (JSON)