mlsanityData to 7 Oct 2026

Bootstrap Your Own Correspondences

arXiv 2106.00677 ↗First posted 1 Jun 2021cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Geometric feature extraction is a crucial component of point cloud registration pipelines. Recent work has demonstrated how supervised learning can be leveraged to learn better and more compact 3D features. However, those approaches' reliance on ground-truth annotation limits their scalability. We propose BYOC: a self-supervised approach that learns visual and geometric features from RGB-D video without relying on ground-truth pose or correspondence. Our key observation is that randomly-initialized CNNs readily provide us with good correspondences; allowing us to bootstrap the learning of both visual and geometric features. Our approach combines classic ideas from point cloud registration with more recent representation learning approaches. We evaluate our approach on indoor scene datasets and find that our method outperforms traditional and learned descriptors, while being competitive with current state-of-the-art supervised approaches.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 39 of its 67 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

39 of 67 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  5. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  7. 2017Deep Image Priorcited by 1,097
  8. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  9. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  10. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  11. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  12. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
27 more
  1. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 338
  2. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  3. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  4. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  5. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  6. 2020Deep Global Registrationcited by 228
  7. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  8. 2019Scaling and Benchmarking Self-Supervised Visual Representation Learningcited by 201
  9. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 181
  10. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 180
  11. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 175
  12. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  13. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  14. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 140
  15. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  16. 2020Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondencescited by 108
  17. 20183D Point Capsule Networkscited by 106
  18. 20183DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registrationcited by 100
  19. 2020DeepGMR: Learning Latent Gaussian Mixture Models for Registrationcited by 91
  20. 2020Learning multiview 3D point cloud registrationcited by 78
  21. 2015Sparse 3D convolutional neural networkscited by 71
  22. 2020End-to-End Learning Local Multi-view Descriptors for 3D Point Cloudscited by 47
  23. 2017Learning Compact Geometric Featurescited by 45
  24. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  25. 2020PointGMM: a Neural GMM Network for Point Cloudscited by 33
  26. 20193D Local Features for Direct Pairwise Registrationcited by 26
  27. 2018Intriguing Properties of Randomly Weighted Networks: Generalizing While Learning Next to Nothingcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 6; 2024: 8; 2025: 5; 2026: 1.

27 papers.

Sort:

By area:

  1. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  2. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  3. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  4. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  5. 2022Towards Federated Learning against Noisy Labels via Local Self-Regularizationcited by 26
  6. 2023Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotationcited by 18
  7. 2023Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priorscited by 15
  8. 2024Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extensioncited by 15
  9. 2023PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registrationcited by 14
  10. 2023PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometrycited by 13
  11. 2022Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformationcited by 12
  12. 2022Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalizationcited by 6
15 more
  1. 2023ZeroReg: Zero-Shot Point Cloud Registration with Foundation Modelscited by 6
  2. 2022Self-Supervised Correspondence Estimation via Multiview Registrationcited by 5
  3. 2025RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learningcited by 5
  4. 2024Unsupervised Point Cloud Registration with Self-Distillationcited by 4
  5. 2025Unlocking Generalization Power in LiDAR Point Cloud Registrationcited by 4
  6. 2023M33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understandingcited by 2
  7. 2024RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registrationcited by 2
  8. 20243D Registration in 30 Years: A Surveycited by 2
  9. 2024Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registrationcited by 1
  10. 2024F2M-Reg: Unsupervised RGB-D Point Cloud Registration with Frame-to-Model Optimizationcited by 0
  11. 2024A Two-Stage Progressive Pre-training using Multi-Modal Contrastive Masked Autoencoderscited by 0
  12. 2025DINOReg: Strong Point Cloud Registration with Vision Foundation Modelcited by 0
  13. 2025Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registrationcited by 0
  14. 2025ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidancecited by 0
  15. 2026GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusioncited by 0