mlsanityData to 14 Oct 2026

PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsampling

arXiv 2109.09337 ↗First posted 20 Sep 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Point cloud upsampling is to densify a sparse point set acquired from 3D sensors, providing a denser representation for the underlying surface. Existing methods divide the input points into small patches and upsample each patch separately, however, ignoring the global spatial consistency between patches. In this paper, we present a novel method PC2-PU, which explores patch-to-patch and point-to-point correlations for more effective and robust point cloud upsampling. Specifically, our network has two appealing designs: (i) We take adjacent patches as supplementary inputs to compensate the loss structure information within a single patch and introduce a Patch Correlation Module to capture the difference and similarity between patches. (ii) After augmenting each patch's geometry, we further introduce a Point Correlation Module to reveal the relationship of points inside each patch to maintain the local spatial consistency. Extensive experiments on both synthetic and real scanned datasets demonstrate that our method surpasses previous upsampling methods, particularly with the noisy inputs. The code and data are at urlhttps://github.com/chenlongwhu/PC2-PU.git.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 28 of its 59 references that are in the map. First posted on arXiv 20 Sep 2021.

Builds on

28 of 59 references.

References · 28

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2020Point Transformercited by 1,470
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  9. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  10. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 146
  11. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  12. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
16 more
  1. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  2. 2021Score-Based Point Cloud Denoisingcited by 83
  3. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  4. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  5. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69
  6. 2019PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrievalcited by 68
  7. 2020Differentiable Manifold Reconstruction for Point Cloud Denoisingcited by 52
  8. 20173D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detectioncited by 35
  9. 2021Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloudcited by 35
  10. 2020Deep Magnification-Flexible Upsampling over 3D Point Cloudscited by 27
  11. 2020SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimizationcited by 26
  12. 2021SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Renderingcited by 17
  13. 2019Point Cloud Super Resolution with Adversarial Residual Graph Networkscited by 13
  14. 2021Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstructioncited by 7
  15. 2017Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversitycited by 6
  16. 2021"Zero-Shot" Point Cloud Upsamplingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 3; 2024: 3; 2025: 3; 2026: 1.

11 papers.

  1. 2023Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functionscited by 43
  2. 2023Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsamplingcited by 19
  3. 2021KTNet: Knowledge Transfer for Unpaired 3D Shape Completioncited by 9
  4. 2023SparseDC: Depth Completion from sparse and non-uniform inputscited by 8
  5. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  6. 2024PillarGen: Enhancing Radar Point Cloud Density and Quality via Pillar-based Point Generation Networkcited by 2
  7. 2024EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D cameracited by 1
  8. 2025VoLUT: Efficient Volumetric streaming enhanced by LUT-based super-resolutioncited by 1
  9. 2025PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representationcited by 1
  10. 2025PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Modelscited by 0
  11. 2026Aerial-ground LiDAR place recognition with patch-level self-supervised learning and expanded reciprocal re-rankingcited by 0