mlsanityData to 7 Oct 2026

PU-GAN: a Point Cloud Upsampling Adversarial Network

arXiv 1907.10844 ↗First posted 25 Jul 2019cs.CVcited by 162

Not on the map. Why?

Abstract (arXiv)

Point clouds acquired from range scans are often sparse, noisy, and non-uniform. This paper presents a new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces. To realize a working GAN network, we construct an up-down-up expansion unit in the generator for upsampling point features with error feedback and self-correction, and formulate a self-attention unit to enhance the feature integration. Further, we design a compound loss with adversarial, uniform and reconstruction terms, to encourage the discriminator to learn more latent patterns and enhance the output point distribution uniformity. Qualitative and quantitative evaluations demonstrate the quality of our results over the state-of-the-arts in terms of distribution uniformity, proximity-to-surface, and 3D reconstruction quality.

Key facts. Cited by 162 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 46; 2023: 33; 2024: 18; 2025: 29; 2026: 8.

162 papers.

Sort:

By area:

  1. 2023Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Followingcited by 192
  2. 2021Multimodal Virtual Point 3D Detectioncited by 166
  3. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  4. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  5. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
  6. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  7. 2021Score-Based Point Cloud Denoisingcited by 83
  8. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  9. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  10. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  11. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  12. 2022AvatarGen: A 3D Generative Model for Animatable Human Avatarscited by 59
38 more
  1. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  2. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  3. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  4. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  5. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  6. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
  7. 2022Low-Rank Tensor Function Representation for Multi-Dimensional Data Recoverycited by 45
  8. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  9. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
  10. 2022Density-preserving Deep Point Cloud Compressioncited by 39
  11. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  12. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  13. 2023OmniAvatar: Geometry-Guided Controllable 3D Head Synthesiscited by 34
  14. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  15. 2021Orienting Point Clouds with Dipole Propagationcited by 31
  16. 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 28
  17. 2023A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsamplingcited by 28
  18. 2021Deep Point Set Resampling via Gradient Fieldscited by 24
  19. 2022Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representationcited by 24
  20. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  21. 2024Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Cloudscited by 24
  22. 2021ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimationcited by 20
  23. 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorizationcited by 20
  24. 2022PD-Flow: A Point Cloud Denoising Framework with Normalizing Flowscited by 19
  25. 2022Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysiscited by 19
  26. 2023Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsamplingcited by 19
  27. 2022PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsamplingcited by 18
  28. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17
  29. 2021SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Renderingcited by 17
  30. 2022PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsamplingcited by 16
  31. 2023PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clusteringcited by 15
  32. 2022Point Cloud Upsampling via Cascaded Refinement Networkcited by 14
  33. 2022Sparse2Dense: Learning to Densify 3D Features for 3D Object Detectioncited by 14
  34. 2022Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Librarycited by 14
  35. 2024En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Datacited by 14
  36. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  37. 2021PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsamplingcited by 11
  38. 2023GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Modelscited by 11

50 most cited of 162 All 162 (JSON)