{"ID":2865510,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22592","arxiv_id":"2509.22592","title":"OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation","abstract":"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.","short_abstract":"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 infe...","url_abs":"https://arxiv.org/abs/2509.22592","url_pdf":"https://arxiv.org/pdf/2509.22592v3","authors":"[\"Elaheh Akbari\",\"Shansita Sharma\",\"Ping He\",\"Ahmadreza Moradipari\",\"Kyungtae Han\",\"Hamed Pirsiavash\",\"Yikun Bai\",\"Soheil Kolouri\"]","published":"2025-09-26T17:12:19Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}