Rectified Point Flow: Generic Point Cloud Pose Estimation

• URL: http://arxiv.org/abs/2506.05282v1
• Date: Thu, 05 Jun 2025 17:36:03 GMT
• Title: Rectified Point Flow: Generic Point Cloud Pose Estimation
• Authors: Tao Sun, Liyuan Zhu, Shengyu Huang, Shuran Song, Iro Armeni,
• Abstract summary: 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.<n>Our method learns a continuous point-wise velocity field that transports noisy points toward their target positions, from which part poses are recovered.
• Score: 25.666110213663828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/.

Related papers

• PKSS-Align: Robust Point Cloud Registration on Pre-Kendall Shape Space [15.151282762403305]
  The proposed method measures shape-based similarity between point clouds on the Pre-Kendall shape space (PKSS), textcolorblackwhich is a shape measurement-based scheme and doesn't require point-to-point or point-to-plane metric.<n>Based on a simple parallel acceleration, it can achieve significant improvement for efficiency and feasibility in practice.
  arXiv  Detail & Related papers  (2025-08-06T10:17:42Z)
• SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance [35.92382553956322]
  We introduce SymmCompletion, a highly effective completion method based on symmetry guidance.<n>Our method comprises two primary components: a Local Symmetry Transformation Network (LSTNet) and a Symmetry-Guidance Transformer (SGFormer)
  arXiv  Detail & Related papers  (2025-03-23T09:45:37Z)
• Fully-Geometric Cross-Attention for Point Cloud Registration [51.865371511201765]
  Point cloud registration approaches often fail when the overlap between point clouds is low due to noisy point correspondences.<n>This work introduces a novel cross-attention mechanism tailored for Transformer-based architectures that tackles this problem.<n>We integrate the Gromov-Wasserstein distance into the cross-attention formulation to jointly compute distances between points across different point clouds.<n>At the point level, we also devise a self-attention mechanism that aggregates the local geometric structure information into point features for fine matching.
  arXiv  Detail & Related papers  (2025-02-12T10:44:36Z)
• SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid Registration [76.40993825836222]
  We propose SPARE, a novel formulation that utilizes a symmetrized point-to-plane distance for robust non-rigid registration. The proposed method greatly improves the accuracy of non-rigid registration problems and maintains relatively high solution efficiency.
  arXiv  Detail & Related papers  (2024-05-30T15:55:04Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• Learning to Register Unbalanced Point Pairs [10.369750912567714]
  Recent 3D registration methods can effectively handle large-scale or partially overlapping point pairs. We present a novel 3D registration method, called UPPNet, for the unbalanced point pairs.
  arXiv  Detail & Related papers  (2022-07-09T08:03:59Z)
• Deep Confidence Guided Distance for 3D Partial Shape Registration [14.315501760755609]
  We present a novel non-iterative learnable method for partial-to-partial 3D shape registration. We present Confidence Guided Distance Network (CGD-net), where we fuse learnable similarity between point embeddings and spatial distance between point clouds.
  arXiv  Detail & Related papers  (2022-01-27T08:40:05Z)
• Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization [105.14877281665011]
  We present SyNoRiM, a novel way to register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds. We demonstrate via extensive experiments that our method achieves a state-of-the-art performance in registration accuracy.
  arXiv  Detail & Related papers  (2021-11-25T02:37:59Z)
• Deep Hough Voting for Robust Global Registration [52.40611370293272]
  We present an efficient framework for pairwise registration of real-world 3D scans, leveraging Hough voting in the 6D transformation parameter space. Our method outperforms state-of-the-art methods on 3DMatch and 3DLoMatch benchmarks while achieving comparable performance on KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-09-09T14:38:06Z)
• Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes [47.49826669394906]
  We propose an unsupervised learning framework for finding dense correspondences between point cloud shapes. In order to learn discriminative pointwise features from point cloud data, we incorporate in the formulation a regularization term based on Sinkhorn normalization. We show that the learned pointwise features can be leveraged by supervised methods to improve the part segmentation performance.
  arXiv  Detail & Related papers  (2020-07-19T05:21:33Z)
• FKAConv: Feature-Kernel Alignment for Point Cloud Convolution [75.85619090748939]
  We provide a formulation to relate and analyze a number of point convolution methods. We also propose our own convolution variant, that separates the estimation of geometry-less kernel weights. We show competitive results on classification and semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2020-04-09T10:12:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.