filename     : ber14a.pdf
entry        : article
conference   : ACM SIGGRAPH 2014, VANCOUVER, 10-14 AUGUST, 2014
pages        : 13:1--13:12
year         : 2014
month        : apr
title        : Facial Performance Enhancement Using Dynamic Shape Space Analysis
subtitle     :
author       : Bermano, Amit H. and Bradley, Derek and Beeler, Thabo and Z\"{u}nd, Fabio and Nowrouzezahrai, Derek and Baran, Ilya and Sorkine-Hornung, Olga and Pfister, Hanspeter and Sumner, Robert W. and Bickel, Bernd and Gross, Markus
booktitle    : ACM Trans. Graph.
ISSN/ISBN    : 0730-0301
editor       : 
publisher    : ACM
publ.place   : New York, NY, USA
volume       : 33
issue        : 2
language     : English
keywords     : Facial animation, data-driven upsampling, performance enhancement
abstract     : The facial performance of an individual is inherently rich in subtle deformation and timing details. Although these subtleties make the performance realistic and compelling, they often elude both motion capture and hand animation. We present a technique for adding fine-scale details and expressiveness to low-resolution art-directed facial performances, such as those created manually using a rig, via marker-based capture, by fitting a morphable model to a video, or through Kinect reconstruction using recent faceshift technology. We employ a high-resolution facial performance capture system to acquire a representative performance of an individual in which he or she explores the full range of facial expressiveness. From the captured data, our system extracts an expressiveness model that encodes subtle spatial and temporal deformation details specific to that particular individual. Once this model has been built, these details can be transferred to low-resolution art-directed performances. We demonstrate results on various forms of input; after our enhancement, the resulting animations exhibit the same nuances and fine spatial details as the captured performance, with optional temporal enhancement to match the dynamics of the actor. Finally, we show that our technique outperforms the current state-of-the-art in example-based facial animation.