ECCV 2026Oral · Best Paper Candidate

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

Yue Pan, Tao Sun, Liyuan Zhu, Lucas Nunes, Iro Armeni, Jens Behley, Cyrill Stachniss

European Conference on Computer Vision (ECCV) 2026

RAP aligns multiple colored point clouds into a shared 3D scene across objects, indoor rooms, and outdoor environments. — RAP learns to transport points into a shared registered scene.

Abstract

Point cloud registration aligns multiple unposed point clouds into a common frame, a core capability for 3D reconstruction and robot localization. We cast 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. The resulting model performs strongly across pairwise and multi-view registration benchmarks, particularly under low overlap, and generalizes across scales and sensor modalities.

BibTeX

@inproceedings{pan2026rap,
  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},
  booktitle={European Conference on Computer Vision},
  year={2026},
  url={https://arxiv.org/abs/2512.01850}
}