mlsanityData to 7 Oct 2026

Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey

arXiv 2407.17877 ↗First posted 25 Jul 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of deep learning (DL). However, the latter faces various issues, including the lack of data or annotated data, the existence of a significant gap between training data and test data, and the requirement for high computational resources. To that end, deep transfer learning (DTL), which decreases dependency and costs by utilizing knowledge gained from a source data/task in training a target data/task, has been widely investigated. Numerous DTL frameworks have been suggested for aligning point clouds obtained from several scans of the same scene. Additionally, DA, which is a subset of DTL, has been modified to enhance the point cloud data's quality by dealing with noise and missing points. Ultimately, fine-tuning and DA approaches have demonstrated their effectiveness in addressing the distinct difficulties inherent in point cloud data. This paper presents the first review shedding light on this aspect. it provides a comprehensive overview of the latest techniques for understanding 3DPC using DTL and domain adaptation (DA). Accordingly, DTL's background is first presented along with the datasets and evaluation metrics. A well-defined taxonomy is introduced, and detailed comparisons are presented, considering different aspects such as different knowledge transfer strategies, and performance. The paper covers various applications, such as 3DPC object detection, semantic labeling, segmentation, classification, registration, downsampling/upsampling, and denoising. Furthermore, the article discusses the advantages and limitations of the presented frameworks, identifies open challenges, and suggests potential research directions.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 112 of its 249 references that are in the map. First posted on arXiv 25 Jul 2024.

Builds on

112 of 249 references.

References · 112

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  9. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  10. 2017Deep Setscited by 1,394
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  12. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
38 more
  1. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  4. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  5. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  8. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  9. 2018A Survey on Deep Transfer Learningcited by 417
  10. 2018PCN: Point Completion Networkcited by 382
  11. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  12. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  13. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  14. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  15. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  16. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  17. 2018Explicit Inductive Bias for Transfer Learning with Convolutional Networkscited by 226
  18. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  19. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  20. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  21. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  22. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  23. 2017Pointwise Convolutional Neural Networkscited by 126
  24. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  25. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  26. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  27. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  28. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  29. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  30. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  31. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 75
  32. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  33. 2018Self-Supervised Model Adaptation for Multimodal Semantic Segmentationcited by 73
  34. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  35. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  36. 2021VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptationcited by 69
  37. 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
  38. 2020ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentationcited by 56

50 most cited of 112 All 112 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2024Applications of Knowledge Distillation in Remote Sensing: A Surveycited by 8
  2. 2025Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detectioncited by 4
  3. 2025Recent Advances in Transformer and Large Language Models for UAV Applicationscited by 3
  4. 2025Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognitioncited by 3
  5. 2024Deep Learning Techniques for Hand Vein Biometrics: A Comprehensive Reviewcited by 2
  6. 2025Deep Learning For Point Cloud Denoising: A Surveycited by 0
  7. 2025Multimodal Robust Prompt Distillation for 3D Point Cloud Modelscited by 0
  8. 2026AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splattingcited by 0
  9. 2026Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flowscited by 0