# Self-Supervised Point Cloud Registration with Deep Versatile Descriptors

arXiv: https://arxiv.org/abs/2201.10034 · HTML: https://mlsanity.com/paper/2201.10034/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 74 references that are in the map.
- First posted on arXiv 25 Jan 2022.

## Builds on (most cited first, 30 of 31)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://mlsanity.com/paper/1908.04616/) (2019)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [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)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://mlsanity.com/paper/1605.03344/) (2016)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)
- [Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences](https://mlsanity.com/paper/2005.01014/) (2020)
- [Self-Supervised Learning for Domain Adaptation on Point-Clouds](https://mlsanity.com/paper/2003.12641/) (2020)
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://mlsanity.com/paper/2008.09088/) (2020)
- [A comprehensive survey on point cloud registration](https://mlsanity.com/paper/2103.02690/) (2021)
- [Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds](https://mlsanity.com/paper/2003.12971/) (2020)
- [PCRNet: Point Cloud Registration Network using PointNet Encoding](https://mlsanity.com/paper/1908.07906/) (2019)
- [OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration](https://mlsanity.com/paper/2103.00937/) (2021)
- [SegICP: Integrated Deep Semantic Segmentation and Pose Estimation](https://mlsanity.com/paper/1703.01661/) (2017)
- [3D Local Features for Direct Pairwise Registration](https://mlsanity.com/paper/1904.04281/) (2019)
- [GOGMA: Globally-Optimal Gaussian Mixture Alignment](https://mlsanity.com/paper/1603.00150/) (2016)
- [The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation](https://mlsanity.com/paper/1812.01232/) (2018)
- [Point Cloud Registration using Representative Overlapping Points](https://mlsanity.com/paper/2107.02583/) (2021)

## Built on by (most cited first, 10 of 10)

- [Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting](https://mlsanity.com/paper/2312.10070/) (2023)
- [Weakly-supervised Camera Localization by Ground-to-satellite Image Registration](https://mlsanity.com/paper/2409.06471/) (2024)
- [Unsupervised Point Cloud Registration with Self-Distillation](https://mlsanity.com/paper/2409.07558/) (2024)
- [Self-Supervised Multi-Frame Neural Scene Flow](https://mlsanity.com/paper/2403.16116/) (2024)
- [Deep Loss Convexification for Learning Iterative Models](https://mlsanity.com/paper/2411.10649/) (2024)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [Rethinking Metrics and Diffusion Architecture for 3D Point Cloud Generation](https://mlsanity.com/paper/2511.05308/) (2025)
- [Context-Conditioned Spatio-Temporal Predictive Learning for Reliable V2V Channel Prediction](https://mlsanity.com/paper/2409.09978/) (2024)
- [Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding](https://mlsanity.com/paper/2507.17533/) (2025)
- [Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction](https://mlsanity.com/paper/2605.22017/) (2026)

## Abstract (arXiv)

As a fundamental yet challenging problem in intelligent transportation systems, point cloud registration attracts vast attention and has been attained with various deep learning-based algorithms. The unsupervised registration algorithms take advantage of deep neural network-enabled novel representation learning while requiring no human annotations, making them applicable to industrial applications. However, unsupervised methods mainly depend on global descriptors, which ignore the high-level representations of local geometries. In this paper, we propose to jointly use both global and local descriptors to register point clouds in a self-supervised manner, which is motivated by a critical observation that all local geometries of point clouds are transformed consistently under the same transformation. Therefore, local geometries can be employed to enhance the representation ability of the feature extraction module. Moreover, the proposed local descriptor is flexible and can be integrated into most existing registration methods and improve their performance. Besides, we also utilize point cloud reconstruction and normal estimation to enhance the transformation awareness of global and local descriptors. Lastly, extensive experimental results on one synthetic and three real-world datasets demonstrate that our method outperforms existing state-of-art unsupervised registration methods and even surpasses supervised ones in some cases. Robustness and computational efficiency evaluations also indicate that the proposed method applies to intelligent vehicles.