发表机构
University of Tübingen; Tübingen AI Center; Technical University of Munich; Munich Center for Machine Learning; Max Planck Institute for Informatics（蒂宾根大学; 蒂宾根人工智能中心; 慕尼黑工业大学; 慕尼黑机器学习中心; 马克斯·普朗克信息学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对三维人体配准的不确定性问题，提出ODin模型，将配准建模为三维扩散过程，实现了更优性能并大幅缩短配准时间。
AI 中文摘要
三维人体配准传统上被视为回归任务，假设模板与输入点云之间存在唯一的真实对齐关系。但实际上，采集噪声、遮挡以及未知的软组织动态会给人体扫描结果带来固有的不确定性，导致基于回归的方法收敛到平均预测结果，往往无法表示合理的几何结构。在本研究中，我们通过将配准建模为对齐分布来接纳这种不确定性，提出了ODin模型，该模型将配准表述为三维扩散过程，在生成与目标几何结构对齐的点云的同时，通过一致的点序保留模板语义。为实现这一点，ODin依赖全局、局部和位置条件来引导每个点到达正确位置。实验表明，这种生成式表述不仅优于其基于回归的基线方法，还达到了新的最优性能，超越了高度工程化的方法，同时将配准时间减少了三分之二。预训练模型和代码可在此httpsURL获取。
英文摘要
3D human registration has historically been treated as a regression task, assuming a unique ground-truth alignment exists between the template and an input point cloud. In reality, acquisition noise, occlusions, and unknown soft tissue dynamics introduce inherent ambiguity into human scans. Regression-based methods consequently converge to an average prediction, often failing to represent a plausible geometry. In our work, we embrace such uncertainty by modeling the registration as a distribution of alignments. We propose ODin, which formulates registration as a 3D diffusion process that generates a point cloud aligned with the target geometry while preserving template semantics through consistent point ordering. To achieve this, ODin relies on global, local, and positional conditioning, guiding each point to its correct location. Our experiments demonstrate that such a generative formulation not only outperforms its regression-based baseline, but also establishes a new state of the art, surpassing highly engineered methods while reducing the registration time by two-thirds. Pre-trained models and code are available at https://riccardomarin.github.io/odin/.
CommentsAccepted at GCPR 2026
