DPHMs：用于基于深度追踪的扩散参数化头部模型
DPHMs: Diffusion Parametric Head Models for Depth-based Tracking
AI总结：
本文提出 DPHMs，利用潜在扩散先验约束身份与表情编码，提升从含噪单目深度序列进行体积头部重建和表情追踪的鲁棒性。
摘要：
我们提出了 Diffusion Parametric Head Models（DPHMs，扩散参数化头部模型），这是一种能够从单目深度序列实现鲁棒体积头部重建与追踪的生成模型。尽管 NPHM 等近期体积头部模型已能出色表示高保真头部几何，但由于对局部且含噪观测的拟合约束不足，从真实单视图深度序列追踪和重建头部仍然极具挑战。为应对这些挑战，我们提出一种基于潜在扩散的先验，用于正则化体积头部重建与追踪。该基于先验的正则项有效约束身份码和表情码，使其位于表示合理头部形状的底层潜在流形上。为评估该扩散先验的有效性，我们采集了一个单目 Kinect 序列数据集，其中包含多种复杂面部表情运动和快速转换。我们将本方法与最先进的追踪方法进行比较，证明其改善了头部身份重建，并实现了鲁棒的表情追踪。
英文摘要：
We introduce Diffusion Parametric Head Models (DPHMs), a generative model that enables robust volumetric head reconstruction and tracking from monocular depth sequences. While recent volumetric head models, such as NPHMs, can now excel in representing high-fidelity head geometries, tracking and reconstructing heads from real-world single-view depth sequences remains very challenging, as the fitting to partial and noisy observations is underconstrained. To tackle these challenges, we propose a latent diffusion-based prior to regularize volumetric head reconstruction and tracking. This prior-based regularizer effectively constrains the identity and expression codes to lie on the underlying latent manifold which represents plausible head shapes. To evaluate the effectiveness of the diffusion-based prior, we collect a dataset of monocular Kinect sequences consisting of various complex facial expression motions and rapid transitions. We compare our method to state-of-the-art tracking methods and demonstrate improved head identity reconstruction as well as robust expression tracking.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
