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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Akbari, Elaheh, Sharma, Shansita, He, Ping, Moradipari, Ahmadreza, Han, Kyungtae, Pirsiavash, Hamed, Bai, Yikun, Kolouri, Soheil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911527222640640
author Akbari, Elaheh
Sharma, Shansita
He, Ping
Moradipari, Ahmadreza
Han, Kyungtae
Pirsiavash, Hamed
Bai, Yikun
Kolouri, Soheil
author_facet Akbari, Elaheh
Sharma, Shansita
He, Ping
Moradipari, Ahmadreza
Han, Kyungtae
Pirsiavash, Hamed
Bai, Yikun
Kolouri, Soheil
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22592
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation
Akbari, Elaheh
Sharma, Shansita
He, Ping
Moradipari, Ahmadreza
Han, Kyungtae
Pirsiavash, Hamed
Bai, Yikun
Kolouri, Soheil
Machine Learning
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.
title OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation
topic Machine Learning
url https://arxiv.org/abs/2509.22592