# Bootstrap Your Own Correspondences

arXiv: https://arxiv.org/abs/2106.00677 · HTML: https://mlsanity.com/paper/2106.00677/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 67 references that are in the map.
- First posted on arXiv 1 Jun 2021.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Scaling and Benchmarking Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1905.01235/) (2019)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [PPFNet: Global Context Aware Local Features for Robust 3D Point Matching](https://mlsanity.com/paper/1802.02669/) (2018)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [The Perfect Match: 3D Point Cloud Matching with Smoothed Densities](https://mlsanity.com/paper/1811.06879/) (2018)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses](https://mlsanity.com/paper/1905.04132/) (2019)
- [Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences](https://mlsanity.com/paper/2005.01014/) (2020)
- [3D Point Capsule Networks](https://mlsanity.com/paper/1812.10775/) (2018)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)

## Built on by (most cited first, 27 of 27)

- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://mlsanity.com/paper/2203.00680/) (2022)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [Lepard: Learning partial point cloud matching in rigid and deformable scenes](https://mlsanity.com/paper/2111.12591/) (2021)
- [Towards Federated Learning against Noisy Labels via Local Self-Regularization](https://mlsanity.com/paper/2208.12807/) (2022)
- [Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation](https://mlsanity.com/paper/2303.11329/) (2023)
- [Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors](https://mlsanity.com/paper/2302.14746/) (2023)
- [Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension](https://mlsanity.com/paper/2403.03532/) (2024)
- [PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration](https://mlsanity.com/paper/2308.04782/) (2023)
- [PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry](https://mlsanity.com/paper/2302.14418/) (2023)
- [Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation](https://mlsanity.com/paper/2208.14893/) (2022)
- [Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization](https://mlsanity.com/paper/2211.15059/) (2022)
- [ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models](https://mlsanity.com/paper/2312.03032/) (2023)
- [Self-Supervised Correspondence Estimation via Multiview Registration](https://mlsanity.com/paper/2212.03236/) (2022)
- [Unlocking Generalization Power in LiDAR Point Cloud Registration](https://mlsanity.com/paper/2503.10149/) (2025)
- [RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning](https://mlsanity.com/paper/2507.19950/) (2025)
- [Unsupervised Point Cloud Registration with Self-Distillation](https://mlsanity.com/paper/2409.07558/) (2024)
- [M33D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding](https://mlsanity.com/paper/2309.15313/) (2023)
- [RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registration](https://mlsanity.com/paper/2405.07594/) (2024)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2411.01870/) (2024)
- [F2M-Reg: Unsupervised RGB-D Point Cloud Registration with Frame-to-Model Optimization](https://mlsanity.com/paper/2405.00507/) (2024)
- [A Two-Stage Progressive Pre-training using Multi-Modal Contrastive Masked Autoencoders](https://mlsanity.com/paper/2408.02245/) (2024)
- [DINOReg: Strong Point Cloud Registration with Vision Foundation Model](https://mlsanity.com/paper/2509.24370/) (2025)
- [Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration](https://mlsanity.com/paper/2510.14354/) (2025)
- [ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance](https://mlsanity.com/paper/2511.22908/) (2025)
- [GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion](https://mlsanity.com/paper/2604.17721/) (2026)

## 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.