用流匹配提升医学点云补全，速度更快且效果更优。
MedPCFM: Improving Medical Point Cloud Completion by Integrating Point Transformers and Flow Matching
- 基于Point Transformer和流匹配构建生成模型PCFM
- 在多个数据集上达到顶尖生成性能，采样步数少于扩散模型
- 模型规模与点数增加时表现持续提升，适合临床重建应用
医学点云补全是解剖重建与临床流程的关键，但该领域的生成建模研究仍不充分。本文通过连续时间生成建模方法，提出基于PTv3的流匹配模型PCFM，用于医学点云补全。在SkullFix、SkullBreak及最新发布的Mandibular Defect数据集上评估，对比了基于PTv3的确定性编码器-解码器模型与采用PVCNN和PTv3作为去噪器的扩散模型（PCDiff）等基线。PCFM在保持与确定性基线相当性能的同时，在各数据集上均实现最先进生成效果，且采样步骤显著减少。在最优配置下，使用PTv3的PCFM相较PVCNN基底提速最高达7倍。此外，通过调整模型规模与点数，分析了经验缩放趋势，发现更高点分辨率带来持续增益，并揭示了模型尺度间的有效权衡。
原文摘要 · Abstract (English)
Medical point cloud completion is important for anatomical reconstruction and downstream clinical workflows, yet generative modeling in this setting remains insufficiently studied. We investigate completion through continuous-time generative modeling and introduce PCFM, a PTv3-backed flow matching approach for medical point cloud completion. We evaluate on SkullFix and SkullBreak, and additionally on the more recent Mandibular Defect dataset. We build strong baselines by adapting PTv3 to a deterministic encoder-decoder completion model and by instantiating diffusion completion (PCDiff) with both PVCNN and PTv3 denoisers. PCFM with PTv3 is competitive with the deterministic PTv3 baseline and achieves state-of-the-art generative performance across datasets, while requiring substantially fewer sampling steps than diffusion. At the best operating points, PTv3 also yields clear throughput gains, providing up to a 7$\times$ speed-up for PCFM compared to a PVCNN backbone. Finally, we study empirical scaling trends by varying model size and point cardinality, showing consistent gains with higher point resolution and informative trade-offs across model scales.
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。