发表机构
AGH University of Krakow; Sano Centre for Computational Medicine（克拉科夫AGH科技大学; 萨诺计算医学中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对颅骨植入物生成中推理耗时的问题，提出教师引导端点蒸馏（TED）的一步式流匹配框架，在SkullBreak和SkullFix基准上实现高质量快速生成，每样本仅需0.04秒。
AI 中文摘要
颅骨植入物生成是医学影像中的一项重要任务。近年来，基于点云的生成方法，尤其是流匹配方法，提供了强大的重建质量和高效的采样能力，但在推理过程中仍需要多次神经函数评估。这限制了快速生成多个合理植入物候选方案的可能性。我们提出了教师引导的端点蒸馏（TED），一种用于点云上条件性颅骨植入物生成的简单一步式蒸馏框架。TED通过教师引导的端点监督和几何匹配损失来训练一步式学生模型，同时避免了显式的路径拉直。我们在SkullFix和SkullBreak基准上评估了TED。TED在SkullBreak数据集上取得了最佳的整体性能，在SkullFix上保持竞争力，并在所比较的一步式方法中提供了最强的Chamfer距离性能。此外，TED每个样本生成植入物大约需要0.04秒。这些结果表明，一步式蒸馏可以大幅加速条件性点云植入物生成，而不会牺牲重建质量。
英文摘要
Cranial implant generation is an important task in medical imaging. Recent point cloud based generative methods, particularly flow matching, offer strong reconstruction quality and efficient sampling, but still require multiple neural function evaluations during inference. This limits rapid generation of multiple plausible implant candidates. We propose Teacher-guided Endpoint Distillation (TED), a simple one-step distillation framework for conditional cranial implant generation on point clouds. TED trains a one-step student using teacher-guided endpoint supervision and geometric matching losses, while avoiding explicit path straightening. We evaluate TED on the SkullFix and SkullBreak benchmarks. TED achieves the best overall performance on the SkullBreak dataset, remains competitive on SkullFix, and provides the strongest Chamfer distance performance among the compared one-step methods. In addition, TED generates implants in approximately 0.04s per sample. These results show that one-step distillation can substantially accelerate conditional point cloud implant generation without sacrificing reconstruction quality.
Comments10 pages, 3 figures
