# End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

arXiv: https://arxiv.org/abs/2011.14579 · HTML: https://mlsanity.com/paper/2011.14579/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors](https://mlsanity.com/paper/2109.00182/) (2021)
- [Fast and Robust Registration of Partially Overlapping Point Clouds](https://mlsanity.com/paper/2112.09922/) (2021)
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://mlsanity.com/paper/2102.10788/) (2021)
- [PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer](https://mlsanity.com/paper/2404.14034/) (2024)
- [Point Cloud Registration using Representative Overlapping Points](https://mlsanity.com/paper/2107.02583/) (2021)
- [PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations](https://mlsanity.com/paper/2401.03167/) (2024)
- [Deep Loss Convexification for Learning Iterative Models](https://mlsanity.com/paper/2411.10649/) (2024)
- [DFC: Deep Feature Consistency for Robust Point Cloud Registration](https://mlsanity.com/paper/2111.07597/) (2021)

## Abstract (arXiv)

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation information. In this paper, we present an end-to-end deep-learning based approach to resolve the point cloud registration problem. Firstly, the revised LPD-Net is introduced to extract features and aggregate them with the graph network. Secondly, the self-attention mechanism is utilized to enhance the structure information in the point cloud and the cross-attention mechanism is designed to enhance the corresponding information between the two input point clouds. Based on which, the virtual corresponding points can be generated by a soft pointer based method, and finally, the point cloud registration problem can be solved by implementing the SVD method. Comparison results in ModelNet40 dataset validate that the proposed approach reaches the state-of-the-art in point cloud registration tasks and experiment resutls in KITTI dataset validate the effectiveness of the proposed approach in real applications.Our source code is available at urlhttps://github.com/qiaozhijian/VCR-Net.git