OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |