发表机构
University of South Carolina; University of North Carolina at Chapel Hill; Murdoch University; Johns Hopkins University（南卡罗来纳大学; 北卡罗来纳大学教堂山分校; 莫道克大学; 约翰斯·霍普金斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出验证器引导的PCA增强框架，通过筛选候选并重训扩散模型，在DFAUST上提升生成多样性且保持身体比例一致性，EAUC达0.752。
AI 中文摘要
有限的训练数据多样性制约了3D人体生成建模：保守模型仍接近已观测样本，而探索性模型常违反基本身体比例。我们提出一种验证器引导的增强框架，利用全局和模态局部PCA生成低成本候选，通过对应关系导出的骨骼比例和身体部位几何进行筛选，并在被接受的候选上重新训练扩散模型。弹性配准既提供了分布式PCA所需的模态结构，也提供了无需逐候选身体模型拟合即可进行可扩展筛选所需的密集解剖对应关系。一项盲人研究支持验证器作为保守守门员，倾向于验证器接受的输出而非拒绝的输出。我们分别评估全池验证器接受率以及接受样本的覆盖度和偏离度，并通过EAUC将其结合。在4,498个配准的DFAUST表面上，分布式PCA增强实现了86.32%的接受率、最高的CP-AUC（0.871）和最高的EAUC（0.752），相比仅真实数据和自增强扩散，EAUC提升了32%。这些结果表明，模态局部、验证器引导的提议拓宽了扩散生成，同时保持了与校准身体测量的高度一致性。
英文摘要
Limited training data diversity constrains generative modeling of 3D human bodies: conservative models remain close to observed examples, whereas exploratory models often violate basic body proportions. We introduce a verifier-guided augmentation framework that uses global and mode-local PCA to generate inexpensive candidates, screens them using correspondence-derived skeletal proportions and body-part geometry, and retrains a diffusion model on accepted candidates. Elastic registration provides both the modal structure used by distributed PCA and the dense anatomical correspondence needed for scalable screening without per-candidate body-model fitting. A blinded human study supports the verifier as a conservative gatekeeper, favoring verifier-accepted over rejected outputs. We evaluate full-pool verifier acceptance separately from the coverage and departure of accepted samples and combine them through EAUC. On 4,498 registered DFAUST surfaces, distributed-PCA augmentation achieves 86.32% acceptance, the highest CP-AUC (0.871), and the highest EAUC (0.752), improving EAUC by 32% over real-only and self-augmented diffusion. These results show that mode-local, verifier-guided proposals broaden diffusion generation while maintaining high agreement with calibrated body measurements.
