mlsanityData to 14 Oct 2026

Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions

arXiv 2304.11846 ↗First posted 24 Apr 2023cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction. However,they usually suffer from two critical issues: (1)fixed upsampling rate after one-time training, since the feature expansion unit is customized for each upsampling rate; (2)outliers or shrinkage artifact caused by the difficulty of precisely predicting 3D coordinates or residuals of upsampled points. To adress them, we propose a new framework for accurate point cloud upsampling that supports arbitrary upsampling rates. Our method first interpolates the low-res point cloud according to a given upsampling rate. And then refine the positions of the interpolated points with an iterative optimization process, guided by a trained model estimating the difference between the current point cloud and the high-res target. Extensive quantitative and qualitative results on benchmarks and downstream tasks demonstrate that our method achieves the state-of-the-art accuracy and efficiency.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Builds on 42 of its 50 references that are in the map. First posted on arXiv 24 Apr 2023.

Builds on

42 of 50 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  10. 2020Point Transformercited by 1,470
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2016An overview of gradient descent optimization algorithmscited by 1,033
30 more
  1. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  5. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  6. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  7. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  8. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  9. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  10. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  11. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  12. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  13. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  14. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  15. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
  16. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  17. 2021Score-Based Point Cloud Denoisingcited by 83
  18. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  19. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69
  20. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  21. 2019Neural Point Cloud Rendering via Multi-Plane Projectioncited by 60
  22. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  23. 2022Density-preserving Deep Point Cloud Compressioncited by 39
  24. 2021Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloudcited by 35
  25. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  26. 2020Deep Magnification-Flexible Upsampling over 3D Point Cloudscited by 27
  27. 2022Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representationcited by 24
  28. 2022PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsamplingcited by 16
  29. 2021Deep Feedback Inverse Problem Solvercited by 11
  30. 2021PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsamplingcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 16; 2025: 17; 2026: 5.

43 papers.

Sort:

By area:

  1. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 47
  2. 2023A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsamplingcited by 28
  3. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  4. 2024An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Modelscited by 23
  5. 2024CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformerscited by 21
  6. 2024SAGS: Structure-Aware 3D Gaussian Splattingcited by 21
  7. 2025SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorizationcited by 21
  8. 2023Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsamplingcited by 19
  9. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  10. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 9
  11. 2024Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learningcited by 6
  12. 2024Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinementcited by 4
31 more
  1. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  2. 2025Efficient Point Clouds Upsampling via Flow Matchingcited by 4
  3. 2025Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributescited by 4
  4. 2025A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationcited by 4
  5. 2024Image-Guided Outdoor LiDAR Perception Quality Assessment for Autonomous Drivingcited by 3
  6. 2024Joint Point Cloud Upsampling and Cleaning with Octree-based CNNscited by 3
  7. 2025LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agentscited by 3
  8. 2024Rethinking Data Input for Point Cloud Upsamplingcited by 2
  9. 2024Point Cloud Resampling with Learnable Heat Diffusioncited by 2
  10. 2026SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generationcited by 2
  11. 2023PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit Surfacecited by 1
  12. 2024GaussianPU: A Hybrid 2D-3D Upsampling Framework for Enhancing Color Point Clouds via 3D Gaussian Splattingcited by 1
  13. 2024MBPU: A Plug-and-Play State Space Model for Point Cloud Upsamping with Fast Point Renderingcited by 1
  14. 2024Att2CPC: Attention-Guided Lossy Attribute Compression of Point Cloudscited by 1
  15. 2024PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsamplingcited by 1
  16. 2025Representation Learning of Point Cloud Upsampling in Global and Local Inputscited by 1
  17. 2025VoLUT: Efficient Volumetric streaming enhanced by LUT-based super-resolutioncited by 1
  18. 2025SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Networkcited by 1
  19. 2025Non-uniform Point Cloud Upsampling via Local Manifold Distributioncited by 1
  20. 2025Low-Rank Tensor Recovery via Variational Schatten-p Quasi-Norm and Jacobian Regularizationcited by 1
  21. 2025PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representationcited by 1
  22. 2024Enhancing Sampling Protocol for Point Cloud Classification Against Corruptionscited by 0
  23. 2025Med-PU: Point Cloud Upsampling for High-Fidelity 3D Medical Shape Reconstructioncited by 0
  24. 2025PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Predictioncited by 0
  25. 2025Preserving Topological and Geometric Embeddings for Point Cloud Recoverycited by 0
  26. 2025Point upsampling networks for single-photon sensingcited by 0
  27. 2025PUFM++: Point Cloud Upsampling via Enhanced Flow Matchingcited by 0
  28. 2026SDCM: Simulated Densifying and Compensatory Modeling Fusion for Radar-Vision 3-D Object Detection in Internet of Vehiclescited by 0
  29. 2026Super-Resolution of Airborne Laser Scanning Point Clouds for Forest Inventorycited by 0
  30. 2026T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationcited by 0
  31. 2026PC2-AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devicescited by 0