mlsanityData to 7 Oct 2026

PU-Net: Point Cloud Upsampling Network

arXiv 1801.06761 ↗First posted 21 Jan 2018cs.CV cs.GRcited by 208

Not on the map. Why?

Abstract (arXiv)

Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space. The expanded feature is then split to a multitude of features, which are then reconstructed to an upsampled point set. Our network is applied at a patch-level, with a joint loss function that encourages the upsampled points to remain on the underlying surface with a uniform distribution. We conduct various experiments using synthesis and scan data to evaluate our method and demonstrate its superiority over some baseline methods and an optimization-based method. Results show that our upsampled points have better uniformity and are located closer to the underlying surfaces.

Key facts. Cited by 208 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 50; 2023: 34; 2024: 32; 2025: 43; 2026: 14.

208 papers.

Sort:

By area:

  1. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  2. 2021Multimodal Virtual Point 3D Detectioncited by 166
  3. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 162
  4. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
  5. 2023Neural Kernel Surface Reconstructioncited by 102
  6. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  7. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  8. 2021Score-Based Point Cloud Denoisingcited by 83
  9. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  10. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  11. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  12. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
38 more
  1. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  2. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  3. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  4. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  5. 2021Neural Marching Cubescited by 50
  6. 2021Point-set Distances for Learning Representations of 3D Point Cloudscited by 48
  7. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  8. 2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 46
  9. 2022Low-Rank Tensor Function Representation for Multi-Dimensional Data Recoverycited by 45
  10. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  11. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  12. 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 43
  13. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
  14. 2022Density-preserving Deep Point Cloud Compressioncited by 39
  15. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  16. 2023Attention-based Point Cloud Edge Samplingcited by 37
  17. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  18. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Modelscited by 36
  19. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  20. 2021Orienting Point Clouds with Dipole Propagationcited by 31
  21. 2022GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representationcited by 28
  22. 2023IterativePFN: True Iterative Point Cloud Filteringcited by 28
  23. 2023A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsamplingcited by 28
  24. 2021MPED: Quantifying Point Cloud Distortion based on Multiscale Potential Energy Discrepancycited by 27
  25. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  26. 2021Deep Point Set Resampling via Gradient Fieldscited by 24
  27. 2022Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representationcited by 24
  28. 2021Spatial-Temporal Transformer for 3D Point Cloud Sequencescited by 22
  29. 2022CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completioncited by 22
  30. 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorizationcited by 20
  31. 2022PD-Flow: A Point Cloud Denoising Framework with Normalizing Flowscited by 19
  32. 2022Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysiscited by 19
  33. 2023Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsamplingcited by 19
  34. 2022Boosting 3D Adversarial Attacks with Attacking On Frequencycited by 18
  35. 2022PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsamplingcited by 18
  36. 2024P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoisingcited by 18
  37. 2021Denoise and Contrast for Category Agnostic Shape Completioncited by 17
  38. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17

50 most cited of 208 All 208 (JSON)