# Self-supervised Point Set Local Descriptors for Point Cloud Registration

arXiv: https://arxiv.org/abs/2003.05199 · HTML: https://mlsanity.com/paper/2003.05199/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Training](https://mlsanity.com/paper/2206.11215/) (2022)
- [3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning](https://mlsanity.com/paper/2103.14533/) (2021)
- [SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data](https://mlsanity.com/paper/2308.05410/) (2023)
- [Towards 3D Scene Understanding by Referring Synthetic Models](https://mlsanity.com/paper/2203.10546/) (2022)
- [An Algorithm for the SE(3)-Transformation on Neural Implicit Maps for Remapping Functions](https://mlsanity.com/paper/2206.08712/) (2022)
- [PhotoReg: Photometrically Registering 3D Gaussian Splatting Models](https://mlsanity.com/paper/2410.05044/) (2024)
- [Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training](https://mlsanity.com/paper/2309.16956/) (2023)

## Abstract (arXiv)

In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly solves the transformation between two point sets in one step without correspondences, the proposed method is able to train from one point cloud, by supervising its self-rotation, that we randomly generate. The whole training requires no manual annotation. In several experiments we evaluate the performance of our method on various datasets and compare to other state of the art algorithms. The results show, that our self-supervised learned descriptor achieves equivalent or even better performance than the supervised learned model, while being easier to train and not requiring labeled data.