mlsanityData to 7 Oct 2026

3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning

arXiv 2103.14533 ↗First posted 26 Mar 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We propose a method for generalizing deep learning for 3D point cloud registration on new, totally different datasets. It is based on two components, MS-SVConv and UDGE. Using Multi-Scale Sparse Voxel Convolution, MS-SVConv is a fast deep neural network that outputs the descriptors from point clouds for 3D registration between two scenes. UDGE is an algorithm for transferring deep networks on unknown datasets in a unsupervised way. The interest of the proposed method appears while using the two components, MS-SVConv and UDGE, together as a whole, which leads to state-of-the-art results on real world registration datasets such as 3DMatch, ETH and TUM. The code is publicly available at https://github.com/humanpose1/MS-SVConv .

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

36 of 58 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  5. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  9. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  10. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  11. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  12. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 287
24 more
  1. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  2. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  3. 2020Deep Global Registrationcited by 228
  4. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  5. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  6. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  7. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 175
  8. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  9. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  10. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  11. 2020SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registrationcited by 141
  12. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  13. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 108
  14. 20183D Point Capsule Networkscited by 106
  15. 2020Learning multiview 3D point cloud registrationcited by 78
  16. 2019DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registrationcited by 77
  17. 2020End-to-End Learning Local Multi-view Descriptors for 3D Point Cloudscited by 47
  18. 2020Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Cloudscited by 23
  19. 2020Distinctive 3D local deep descriptorscited by 21
  20. 2018Classification of Point Cloud Scenes with Multiscale Voxel Deep Networkcited by 11
  21. 2016Fine-To-Coarse Global Registration of RGB-D Scanscited by 7
  22. 20183D Point Cloud Descriptors in Hand-crafted and Deep Learning Age: State-of-the-Artcited by 7
  23. 2020Self-supervised Point Set Local Descriptors for Point Cloud Registrationcited by 7
  24. 2020A Benchmark for Point Clouds Registration Algorithmscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 5; 2025: 1; 2026: 1.

11 papers.

  1. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited by 25
  2. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  3. 2024Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Surveycited by 9
  4. 2023COLA: COarse-LAbel multi-source LiDAR semantic segmentation for autonomous drivingcited by 8
  5. 2026IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registrationcited by 5
  6. 2024PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Trainingcited by 4
  7. 2022Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddingscited by 2
  8. 20243D Registration in 30 Years: A Surveycited by 2
  9. 2024First Mapping the Canopy Height of Primeval Forests in the Tallest Tree Area of Asiacited by 1
  10. 2024Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registrationcited by 1
  11. 2025LAHNet: Local Attentive Hashing Network for Point Cloud Registrationcited by 0