mlsanityData to 14 Oct 2026

Rectified Point Flow: Generic Point Cloud Pose Estimation

arXiv 2506.05282 ↗First posted 5 Jun 2025cs.CV cs.AI cs.ROcited by 14

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 58 of its 73 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

58 of 73 references.

References · 58

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  8. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  9. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  10. 2019Root Mean Square Layer Normalizationcited by 1,480
  11. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  12. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
38 more
  1. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  2. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  3. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  4. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  5. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  6. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  7. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  8. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  9. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 283
  10. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  11. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  12. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  13. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  14. 2020RPM-Net: Robust Point Matching using Learned Featurescited by 182
  15. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  16. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 177
  17. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  18. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  19. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  20. 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 95
  21. 2021You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptorscited by 68
  22. 2020Generative 3D Part Assembly via Dynamic Graph Learningcited by 67
  23. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  24. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 60
  25. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 48
  26. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  27. 2021MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronizationcited by 46
  28. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 43
  29. 2022Breaking Bad: A Dataset for Geometric Fracture and Reassemblycited by 41
  30. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 36
  31. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimationcited by 33
  32. 2024DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassemblycited by 33
  33. 2023Jigsaw: Learning to Assemble Multiple Fractured Objectscited by 29
  34. 2023Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assemblycited by 28
  35. 2023IKEA-Manual: Seeing Shape Assembly Step by Stepcited by 22
  36. 2023Category-Level Multi-Part Multi-Joint 3D Shape Assemblycited by 22
  37. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  38. 2024Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policiescited by 18

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 11.

14 papers.

Sort:

By area:

  1. 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matchingcited by 9
  2. 2026TORA: Topological Representation Alignment for 3D Shape Assemblycited by 4
  3. 2025Dense associative memory for Gaussian distributionscited by 2
  4. 2026HomoFM: Deep Homography Estimation with Flow Matchingcited by 1
  5. 2026Generative 6D Pose Estimation via Conditional Flow Matchingcited by 1
  6. 2026CRAG: Can 3D Generative Models Help 3D Assembly?cited by 1
  7. 2026SARe: Structure-Aware Generative 3D Fragment Reassemblycited by 1
  8. 2025ReSeFlow: Rectifying SE(3)-Equivariant Policy Learning Flowscited by 0
  9. 2026LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulationcited by 0
  10. 2026Foundational feature fusion for conditional flow matching in 6D pose estimationcited by 0
  11. 2026BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registrationcited by 0
  12. 2026PART: Learning 3D Part Assembly and Retrieval with Transformerscited by 0
2 more
  1. 2026AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agentscited by 0
  2. 2026LLM2R: From Large Language Models to 3D Reassemblerscited by 0