mlsanityData to 14 Oct 2026

OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation

arXiv 2509.22592 ↗First posted 26 Sep 2025cs.LGcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Flow-matching models have recently emerged as a powerful framework for continuous generative modeling, including 3D point cloud synthesis. However, their deployment is limited by the need for multiple sequential sampling steps at inference time. MeanFlow enables single-step generation and significantly accelerates inference, but often struggles to approximate the trajectories of the original multi-step flow, leading to degraded sample quality. In this work, we propose an Optimal Transport-enhanced MeanFlow framework (OT-MF3D) for efficient and accurate 3D point cloud generation and completion. By incorporating optimal transport-based sampling, our method better preserves the geometric and distributional structure of the underlying multi-step flow while retaining single-step inference. Experiments on ShapeNet show improved generation and completion quality compared to recent baselines, while reducing training and inference costs relative to conventional diffusion and flow-based models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 32 of its 46 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

32 of 46 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025A Continuous-Time Consistency Model for 3D Point Cloud Generation1 Sep
  2. 2022Fast Point Cloud Generation with Straight Flows4 Dec
  3. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  4. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  9. 2023Consistency Modelscited by 1,822
  10. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  11. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  12. 2025Mean Flows for One-step Generative Modelingcited by 561
16 more
  1. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  2. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  3. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  4. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplingscited by 278
  5. 2020Learning Gradient Fields for Shape Generationcited by 245
  6. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  7. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  8. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 98
  9. 2020Discrete Point Flow Networks for Efficient Point Cloud Generationcited by 87
  10. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
  11. 2024Optimal Flow Matching: Learning Straight Trajectories in Just One Stepcited by 78
  12. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  13. 2024Simple ReFlow: Improved Techniques for Fast Flow Modelscited by 34
  14. 2025Not-So-Optimal Transport Flows for 3D Point Cloud Generationcited by 17
  15. 2025Beyond Optimal Transport: Model-Aligned Coupling for Flow Matchingcited by 15
  16. 2024Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matchingcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MFM-point: Multi-scale Flow Matching for Point Cloud Generation
  2. 2026Hierarchical Flow Matching for 3D Point Cloud Generation
  3. 2024Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
  4. 2026Point-MF: Stabilizing One-Step Mean Flows for Single-Image Point Cloud Reconstruction
  5. 2026Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors
  6. 2026GridFlow: Structured Latent Flow for Seamless City-Scale 3D Point Cloud Generation
  7. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
  8. 2025PUFM++: Point Cloud Upsampling via Enhanced Flow Matching