mlsanityData to 7 Oct 2026

3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration

arXiv 1807.09413 ↗First posted 25 Jul 2018cs.CVcited by 100

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision. Unlike many existing works, we do not require manual annotation of matching point clusters. Instead, we leverage on alignment and attention mechanisms to learn feature correspondences from GPS/INS tagged 3D point clouds without explicitly specifying them. We create training and benchmark outdoor Lidar datasets, and experiments show that 3DFeat-Net obtains state-of-the-art performance on these gravity-aligned datasets.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 25; 2023: 25; 2024: 12; 2025: 5; 2026: 4.

100 papers.

Sort:

By area:

  1. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 200
  2. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 151
  3. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  4. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 94
  5. 2021A comprehensive survey on point cloud registrationcited by 84
  6. 2023GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformercited by 83
  7. 2022SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registrationcited by 62
  8. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
  9. 2021DeepI2P: Image-to-Point Cloud Registration via Deep Classificationcited by 58
  10. 2021Deep Hough Voting for Robust Global Registrationcited by 53
  11. 2021HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registrationcited by 47
  12. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
38 more
  1. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  2. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 41
  3. 2023RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registrationcited by 37
  4. 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matchingcited by 35
  5. 2021Bootstrap Your Own Correspondencescited by 27
  6. 2021Self-supervised Geometric Perceptioncited by 26
  7. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  8. 2022RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registrationcited by 25
  9. 2021Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representationscited by 24
  10. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  11. 2022A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environmentscited by 19
  12. 2024KISS-Matcher: Fast and Robust Point Cloud Registration Revisitedcited by 16
  13. 2023Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAMcited by 15
  14. 2024Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extensioncited by 15
  15. 2021FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registrationcited by 14
  16. 2022DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimizationcited by 14
  17. 2024Multiway Point Cloud Mosaicking with Diffusion and Global Optimizationcited by 14
  18. 2021DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registrationcited by 12
  19. 2022Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Trainingcited by 12
  20. 2022ARM3D: Attention-based relation module for indoor 3D object detectioncited by 11
  21. 2023Density-invariant Features for Distant Point Cloud Registrationcited by 11
  22. 2022A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registrationcited by 10
  23. 2021DARE-SLAM: Degeneracy-Aware and Resilient Loop Closing in Perceptually-Degraded Environmentscited by 9
  24. 2023End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localizationcited by 9
  25. 2022VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registrationcited by 8
  26. 2025BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenescited by 8
  27. 2021City-scale Scene Change Detection using Point Cloudscited by 7
  28. 2021Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisationcited by 7
  29. 2021WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registrationcited by 7
  30. 2022Zero NeRF: Registration with Zero Overlapcited by 7
  31. 2021Attention Models for Point Clouds in Deep Learning: A Surveycited by 6
  32. 2021Fully Convolutional Geometric Features for Category-level Object Alignmentcited by 6
  33. 2023Generalizable Local Feature Pre-training for Deformable Shape Analysiscited by 6
  34. 2021Consistent Two-Flow Network for Tele-Registration of Point Cloudscited by 5
  35. 2021End-to-end Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registrationcited by 5
  36. 2021COTReg:Coupled Optimal Transport based Point Cloud Registrationcited by 5
  37. 2022RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Cloudscited by 5
  38. 2022LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloudcited by 5

50 most cited of 100 All 100 (JSON)