mlsanityData to 14 Oct 2026

PU-Transformer: Point Cloud Upsampling Transformer

arXiv 2111.12242 ↗First posted 24 Nov 2021cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Given the rapid development of 3D scanners, point clouds are becoming popular in AI-driven machines. However, point cloud data is inherently sparse and irregular, causing significant difficulties for machine perception. In this work, we focus on the point cloud upsampling task that intends to generate dense high-fidelity point clouds from sparse input data. Specifically, to activate the transformer's strong capability in representing features, we develop a new variant of a multi-head self-attention structure to enhance both point-wise and channel-wise relations of the feature map. In addition, we leverage a positional fusion block to comprehensively capture the local context of point cloud data, providing more position-related information about the scattered points. As the first transformer model introduced for point cloud upsampling, we demonstrate the outstanding performance of our approach by comparing with the state-of-the-art CNN-based methods on different benchmarks quantitatively and qualitatively.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 54 of its 73 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

54 of 73 references.

References · 54

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016Layer Normalizationcited by 5,669
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
38 more
  1. 2017Non-local Neural Networkscited by 2,293
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  3. 2020Point Transformercited by 1,470
  4. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  6. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  7. 2021Transformers in Vision: A Surveycited by 1,013
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  9. 2020Pre-Trained Image Processing Transformercited by 893
  10. 2020PCT: Point cloud transformercited by 732
  11. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  13. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  14. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  15. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  16. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  17. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  18. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  19. 2018PCN: Point Completion Networkcited by 384
  20. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 347
  21. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  22. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  23. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  24. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  25. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  26. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  27. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  28. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  29. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
  30. 2019A Deep Journey into Super-resolution: A surveycited by 86
  31. 2017Deep Projective 3D Semantic Segmentationcited by 81
  32. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  33. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  34. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69
  35. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45
  36. 2021Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloudcited by 35
  37. 2020Deep Magnification-Flexible Upsampling over 3D Point Cloudscited by 27
  38. 2020SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimizationcited by 26

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 8; 2023: 6; 2024: 8; 2025: 8; 2026: 2.

32 papers.

Sort:

By area:

  1. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
  2. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  3. 20223DCTN: 3D Convolution-Transformer Network for Point Cloud Classificationcited by 25
  4. 2022LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformerscited by 21
  5. 2023P2C: Self-Supervised Point Cloud Completion from Single Partial Cloudscited by 20
  6. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  7. 2023TULIP: Transformer for Upsampling of LiDAR Point Cloudscited by 12
  8. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  9. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 9
  10. 2022Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussianscited by 6
  11. 2024Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learningcited by 6
  12. 2023DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstructioncited by 4
20 more
  1. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  2. 2024Joint Point Cloud Upsampling and Cleaning with Octree-based CNNscited by 3
  3. 2022PU-MFA : Point Cloud Up-sampling via Multi-scale Features Attentioncited by 2
  4. 2022CU-Net: Real-Time High-Fidelity Color Upsampling for Point Cloudscited by 2
  5. 2024PillarGen: Enhancing Radar Point Cloud Density and Quality via Pillar-based Point Generation Networkcited by 2
  6. 2024Rethinking Data Input for Point Cloud Upsamplingcited by 2
  7. 2024NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Cloudscited by 2
  8. 2023Parametric Surface Constrained Upsampler Network for Point Cloudcited by 1
  9. 2023PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit Surfacecited by 1
  10. 2024MBPU: A Plug-and-Play State Space Model for Point Cloud Upsamping with Fast Point Renderingcited by 1
  11. 2025Representation Learning of Point Cloud Upsampling in Global and Local Inputscited by 1
  12. 2025SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Networkcited by 1
  13. 2025PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representationcited by 1
  14. 2024Enhancing Sampling Protocol for Point Cloud Classification Against Corruptionscited by 0
  15. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 0
  16. 2025Preserving Topological and Geometric Embeddings for Point Cloud Recoverycited by 0
  17. 2025Point upsampling networks for single-photon sensingcited by 0
  18. 2025PUFM++: Point Cloud Upsampling via Enhanced Flow Matchingcited by 0
  19. 2026A Cookbook of 3D Vision: Data, Learning Paradigms, and Applicationcited by 0
  20. 2026PC2-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devicescited by 0