Deep Energies for Estimating Three-Dimensional Facial Pose and Expression

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：While much progress has been made in capturing high-quality facial performances using motion capture markers and shape-from-shading,high-end systems typically also rely on rotoscope curves hand-drawn on the image.These curves are subjective and difficult to draw consistently;moreover,ad-hoc procedural methods are required for generating match-ing rotoscope curves on synthetic renders embedded in the optimization used to determine three-dimensional(3D)facial pose and expression.We propose an alternative approach whereby these curves and other keypoints are detected automatically on both the image and the synthetic renders using trained neural networks,eliminating artist subjectivity,and the ad-hoc procedures meant to mimic it.More generally,we propose using machine learning networks to implicitly define deep energies which when minimized using classical optimi-zation techniques lead to 3D facial pose and expression estimation.

外文关键词：

Numerical optimizationNeural networksMotion captureFace tracking

作者：

Jane Wu、Michael Bao、Xinwei Yao、Ronald Fedkiw

展开 >

作者单位：

Department of Computer Science,Stanford University,353 Jane Stanford Way,Stanford,CA 94305,USA

Epic Games,620 Crossroads Blvd,Cary,NC 27518,USA

基金：

Office of Naval Research(ONR)Office of Naval Research(ONR)Office of Naval Research(ONR)generous gifts from Amazon and ToyotaVMWare Fellowship in Honor of Ole AgesenStanford School of Engineering Fellowship

项目编号：

N00014-13-1-0346ONR N00014-17-1-2174ARL AHPCRC W911NF-07-0027

出版年：

2024

DOI：

10.1007/s42967-023-00256-y

应用数学与计算数学学报

上海大学

应用数学与计算数学学报

影响因子：0.165

ISSN：1006-6330

年,卷(期)：2024.6(2)