---
license: mit
pipeline_tag: other
tags:
- point-cloud
- 3d-vision
- pose-estimation
- registration
- flow-model
---

# Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching

[![Project Page](https://img.shields.io/badge/Project_Page-RAP-red)](https://register-any-point.github.io/) 
[![arXiv](https://img.shields.io/badge/arXiv-2512.01850-blue?logo=arxiv&color=%23B31B1B)](https://huggingface.co/papers/2512.01850) 
[![GitHub](https://img.shields.io/badge/GitHub-RAP-black?logo=github)](https://github.com/PRBonn/RAP)
[![Demo](https://img.shields.io/badge/Gradio-RAP-red?logo=gradio)](https://f299fbbc3c4f12d152.gradio.live/)

![rap_teaser](https://register-any-point.github.io/images/rap_teaser_new.png)

**Register Any Point (RAP)** is a single-stage multi-view point cloud registration model based on conditional flow matching generation in the Euclidean space. RAP model generalises to point clouds with diverse scales, sensors, view counts, and overlapping ratios. 

## Paper Information

- **Paper**: [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching](https://huggingface.co/papers/2512.01850)
- **Authors**: Yue Pan, Tao Sun, Liyuan Zhu, Lucas Nunes, Iro Armeni, Jens Behley, Cyrill Stachniss.
- **Project Page**: [https://register-any-point.github.io/](https://register-any-point.github.io/)

## Summary

Point cloud registration aligns multiple unposed point clouds into a common reference frame and is a core step for 3D reconstruction and robot localization. RAP casts registration as conditional generation: a learned, continuous point-wise velocity field transports noisy points to a registered scene, from which the pose of each view is recovered. 

Unlike prior methods that perform correspondence matching to estimate pairwise transformations and then optimize a pose graph for multi-view registration, RAP directly generates the registered point cloud, yielding both efficiency and point-level global consistency.

## Installation and Usage

For details on installation and running inference, please check the [official GitHub repository](https://github.com/PRBonn/RAP).

## Citation

If you use RAP in your research, please cite:

```bibtex
@article{pan2025arxiv,
  title = {{Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching}},
  author = {Pan, Yue and Sun, Tao and Zhu, Liyuan and Nunes, Lucas and Armeni, Iro and Behley, Jens and Stachniss, Cyrill},
  journal = {arXiv preprint arXiv:2512.01850},
  year    = {2025}
}
```