Saved in:
Bibliographic Details
Main Authors: Tang, Jiapeng, Dai, Angela, Nie, Yinyu, Markhasin, Lev, Thies, Justus, Niessner, Matthias
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.01068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917632410648576
author Tang, Jiapeng
Dai, Angela
Nie, Yinyu
Markhasin, Lev
Thies, Justus
Niessner, Matthias
author_facet Tang, Jiapeng
Dai, Angela
Nie, Yinyu
Markhasin, Lev
Thies, Justus
Niessner, Matthias
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_01068
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DPHMs: Diffusion Parametric Head Models for Depth-based Tracking
Tang, Jiapeng
Dai, Angela
Nie, Yinyu
Markhasin, Lev
Thies, Justus
Niessner, Matthias
Computer Vision and Pattern Recognition
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.
title DPHMs: Diffusion Parametric Head Models for Depth-based Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.01068