Real-Time 3D Face Fitting and Texture Fusion on In-the-Wild Videos

被引：15

作者：

Huber, Patrik ^{[1
]}

Kopp, Philipp ^{[2
]}

Christmas, William ^{[1
]}

Raetsch, Matthias ^{[2
]}

Kittler, Josef ^{[1
]}

机构：

[1] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford GU2 7XH, Surrey, England

[2] Reutlingen Univ, Image Understanding & Interact Robot Grp, D-72762 Reutlingen, Germany

来源：

IEEE SIGNAL PROCESSING LETTERS | 2017年 / 24卷 / 04期

基金：

英国工程与自然科学研究理事会;

关键词：

Face model fitting; 3D Morphable Face Model; 3D face reconstruction; open source software; real-time;

D O I：

10.1109/LSP.2016.2643284

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

We present a fully automatic approach to real-time 3D face reconstruction from monocular in-the-wild videos. With the use of a cascaded-regressor-based face tracking and a 3D morphable face model shape fitting, we obtain a semidense 3D face shape. We further use the texture information frommultiple frames to build a holistic 3D face representation from the video footage. Our system is able to capture facial expressions and does not require any person-specific training. We demonstrate the robustness of our approach on the challenging 300 Videos in the Wild (300VW) dataset. Our real-time fitting framework is available as an open-source library at http://4dface. org.

引用

页码：437 / 441

页数：5

共 19 条

[1] Inverse Rendering of Faces with a 3D Morphable Model [J].

Aldrian, Oswald ;

Smith, William A. P. .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (05) :1080-1093

[2]

[Anonymous], 2001, Robotica, DOI DOI 10.1017/S0263574700223217

[3]

[Anonymous], 2007, THESIS

[4]

Bas A., 2016, CORR

[5] Real-Time High-Fidelity Facial Performance Capture [J].

Cao, Chen ;

Bradley, Derek ;

Zhou, Kun ;

Beeler, Thabo .

ACM TRANSACTIONS ON GRAPHICS, 2015, 34 (04)

[6] Displaced Dynamic Expression Regression for Real-time Facial Tracking and Animation [J].

Cao, Chen ;

Hou, Qiming ;

Zhou, Kun .

ACM TRANSACTIONS ON GRAPHICS, 2014, 33 (04)

[7] 3D Shape Regression for Real-time Facial Animation [J].

Cao, Chen ;

Weng, Yanlin ;

Lin, Stephen ;

Zhou, Kun .

ACM TRANSACTIONS ON GRAPHICS, 2013, 32 (04)

[8] Random Cascaded-Regression Copse for Robust Facial Landmark Detection [J].

Feng, Zhen-Hua ;

Huber, Patrik ;

Kittler, Josef ;

Christmas, William ;

Wu, Xiao-Jun .

IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (01) :76-80

[9] Reconstructing Detailed Dynamic Face Geometry from Monocular Video [J].

Garrido, Pablo ;

Valgaerts, Levi ;

Wu, Chenglei ;

Theobalt, Christian .

ACM TRANSACTIONS ON GRAPHICS, 2013, 32 (06)

[10]

Huber P., 2016, P INT C COMP VIS THE

← 1 2 →