分层流匹配生成高质量3D点云，效率高且结构清晰。
Hierarchical Flow Matching for 3D Point Cloud Generation
- 分两层建模：先生成紧凑潜在形状，再基于潜码重建细节点云。
- 仅需15步欧拉积分即可采样，训练用MSE损失，计算高效。
- 适合需要结构化生成与下游任务的3D点云研究者使用。
高质量3D点云生成需兼顾全局拓扑与局部几何细节。现有基于流的方法依赖连续归一化流（CNFs），训练中需昂贵的ODE求解与迹估计；扩散模型则需数百次迭代去噪。多数方法直接在点空间进行单层级生成，忽视3D形状天然的层次结构。本文提出分层流匹配（HFM），将流匹配扩展至双层结构，用于无条件3D点云生成。HFM通过最优传输流匹配将任务分解为两步：潜流匹配（Latent Flow Matching）在紧凑潜在空间建模全局形状流形，条件点流匹配（Conditional Point Flow Matching）基于潜码重建细节点云。两类流均采用简单的MSE回归损失训练。所得直通最优传输路径支持高效采样，每流仅需15步欧拉积分；且结构化潜空间可支持下游分类等任务。在ShapeNet与ModelNet基准上的大量实验表明，HFM性能达到或超越现有最先进方法。
原文摘要 · Abstract (English)
Generating high-quality 3D point clouds requires capturing both global shape topology and local geometric details. Existing flow-based methods rely on continuous normalizing flows (CNFs) that demand expensive ODE solving and trace estimation during training, while diffusion models require hundreds of iterative denoising steps. Moreover, most approaches adopt single-level generation directly in point space, disregarding the hierarchical structure natural to 3D shapes. We propose Hierarchical Flow Matching (HFM) that extends flow matching to bilevel structure for unconditional 3D point cloud generation. HFM decomposes the task into two levels via optimal-transport flow matching: a \textit{Latent Flow Matching} models the global shape manifold in a compact latent space, and a \textit{Conditional Point Flow Matching} reconstructs detailed point clouds conditioned on the latent code. Both flows are trained with simple MSE regression losses. The resulting straight OT paths enable efficient sampling with as few as 15 Euler steps per flow, while the structured latent space supports downstream tasks including classification. Extensive experiments on ShapeNet and ModelNet benchmarks demonstrate that HFM achieves competitive or even best performance compared with prior state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。