Rectified Point Flow: Generic Point Cloud Pose Estimation

TAO SUN, Liyuan Zhu, Shengyu Huang, Shuran Song, Iro Armeni

Keywords: Point Cloud Registration, Rectified Flow, Multi-Part Assembly, Shape Assembly

TL;DR: Rectified Point Flow is a single generative model that turns unaligned point clouds into assembled shapes—unifying pairwise registration and multi-part assembly—and sets new state-of-the-art results across five benchmarks.

Abstract: We present Rectified Point Flow, a unified parameterization that formulates pairwise point cloud registration and multi-part shape assembly as a single conditional generative problem. Given unposed point clouds, our method learns a continuous point-wise velocity field that transports noisy points toward their target positions, from which part poses are recovered. In contrast to prior work that regresses part-wise poses with ad-hoc symmetry handling, our method intrinsically learns assembly symmetries without symmetry labels. Together with an overlap-aware encoder focused on inter-part contacts, Rectified Point Flow achieves a new state-of-the-art performance on six benchmarks spanning pairwise registration and shape assembly. Notably, our unified formulation enables effective joint training on diverse datasets, facilitating the learning of shared geometric priors and consequently boosting accuracy. Our code and models are available at https://rectified-pointflow.github.io/.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 2077