DPHMs: Diffusion Parametric Head Models for Depth-based Tracking
CVPR 2024(2023)
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
reconstruction 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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要