校正點流：通用點雲姿態估計

摘要

我们提出了“修正点流”（Rectified Point Flow），这是一种统一的参数化方法，将成对点云配准与多部件形状装配表述为单一的条件生成问题。面对未定位的点云，我们的方法学习一个连续的点速度场，该场将噪声点向目标位置输送，从而恢复出部件的姿态。与先前通过临时对称性处理回归部件姿态的工作不同，我们的方法无需对称性标签即可内在地学习装配对称性。结合专注于重叠点的自监督编码器，我们的方法在涵盖成对配准与形状装配的六个基准测试中实现了新的最先进性能。尤为重要的是，这一统一公式使得在多样化数据集上进行有效联合训练成为可能，促进了共享几何先验的学习，进而提升了准确性。项目页面：https://rectified-pointflow.github.io/。

English

We introduce 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 a self-supervised encoder focused on overlapping points, our method 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. Project page: https://rectified-pointflow.github.io/.

校正點流：通用點雲姿態估計

Rectified Point Flow: Generic Point Cloud Pose Estimation

摘要

Support