mlsanityData to 14 Oct 2026

Deep Learning for 3D Point Cloud Enhancement: A Survey

arXiv 2411.00857 ↗First posted 30 Oct 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Point cloud data now are popular data representations in a number of three-dimensional (3D) vision research realms. However, due to the limited performance of sensors and sensing noise, the raw data usually suffer from sparsity, noise, and incompleteness. This poses great challenges to down-stream point cloud processing tasks. In recent years, deep-learning-based point cloud enhancement methods, which aim to achieve dense, clean, and complete point clouds from low-quality raw point clouds using deep neural networks, are gaining tremendous research attention. This paper, for the first time to our knowledge, presents a comprehensive survey for deep-learning-based point cloud enhancement methods. It covers three main perspectives for point cloud enhancement, i.e., (1) denoising to achieve clean data; (2) completion to recover unseen data; (3) upsampling to obtain dense data. Our survey presents a new taxonomy for recent state-of-the-art methods and systematic experimental results on standard benchmarks. In addition, we share our insightful observations, thoughts, and inspiring future research directions for point cloud enhancement with deep learning.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 136 of its 232 references that are in the map. First posted on arXiv 30 Oct 2024.

Builds on

136 of 232 references.

References · 136

  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. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  7. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  8. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  10. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  11. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  12. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
38 more
  1. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  2. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  3. 2018PCN: Point Completion Networkcited by 384
  4. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  5. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  6. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  7. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
  8. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  9. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  10. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  11. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  12. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  13. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  14. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  15. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  16. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 127
  17. 20203D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Priorcited by 126
  18. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  19. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  20. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  21. 2021Variational Relational Point Completion Networkcited by 104
  22. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  23. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  24. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
  25. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  26. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  27. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 98
  28. 2020PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Pathscited by 97
  29. 2021Contextual Transformer Networks for Visual Recognitioncited by 90
  30. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  31. 2021Score-Based Point Cloud Denoisingcited by 83
  32. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  33. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  34. 2020Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Datacited by 74
  35. 20213D Semantic Scene Completion: a Surveycited by 74
  36. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  37. 2020Detail Preserved Point Cloud Completion via Separated Feature Aggregationcited by 70
  38. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69

50 most cited of 136 All 136 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Groundingcited by 5
  2. 2025Noise2Score3D: Tweedie's Approach for Unsupervised Point Cloud Denoisingcited by 4
  3. 2025MambaTron: Efficient Cross-Modal Point Cloud Enhancement using Aggregate Selective State Space Modelingcited by 2
  4. 2026Meltdown: Circuits and Bifurcations in Point-Cloud-Conditioned 3D Diffusion Transformerscited by 1