---
_id: '2115'
abstract:
- lang: eng
text: 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.
author:
- first_name: Amit
full_name: Bermano, Amit H
last_name: Bermano
- first_name: Derek
full_name: Bradley, Derek J
last_name: Bradley
- first_name: Thabo
full_name: Beeler, Thabo
last_name: Beeler
- first_name: Fabio
full_name: Zund, Fabio
last_name: Zund
- first_name: Derek
full_name: Nowrouzezahrai, Derek
last_name: Nowrouzezahrai
- first_name: Ilya
full_name: Baran, Ilya
last_name: Baran
- first_name: Olga
full_name: Sorkine-Hornung, Olga
last_name: Sorkine Hornung
- first_name: Hanspeter
full_name: Pfister, Hanspeter
last_name: Pfister
- first_name: Robert
full_name: Sumner, Robert W
last_name: Sumner
- first_name: Bernd
full_name: Bernd Bickel
id: 49876194-F248-11E8-B48F-1D18A9856A87
last_name: Bickel
orcid: 0000-0001-6511-9385
- first_name: Markus
full_name: Groß, Markus S
last_name: Groß
citation:
ama: Bermano A, Bradley D, Beeler T, et al. Facial performance enhancement using
dynamic shape space analysis. ACM Transactions on Graphics. 2014;33(2).
doi:10.1145/2546276
apa: Bermano, A., Bradley, D., Beeler, T., Zund, F., Nowrouzezahrai, D., Baran,
I., … Groß, M. (2014). Facial performance enhancement using dynamic shape space
analysis. ACM Transactions on Graphics. ACM. https://doi.org/10.1145/2546276
chicago: Bermano, Amit, Derek Bradley, Thabo Beeler, Fabio Zund, Derek Nowrouzezahrai,
Ilya Baran, Olga Sorkine Hornung, et al. “Facial Performance Enhancement Using
Dynamic Shape Space Analysis.” ACM Transactions on Graphics. ACM, 2014.
https://doi.org/10.1145/2546276.
ieee: A. Bermano et al., “Facial performance enhancement using dynamic shape
space analysis,” ACM Transactions on Graphics, vol. 33, no. 2. ACM, 2014.
ista: Bermano A, Bradley D, Beeler T, Zund F, Nowrouzezahrai D, Baran I, Sorkine
Hornung O, Pfister H, Sumner R, Bickel B, Groß M. 2014. Facial performance enhancement
using dynamic shape space analysis. ACM Transactions on Graphics. 33(2).
mla: Bermano, Amit, et al. “Facial Performance Enhancement Using Dynamic Shape Space
Analysis.” ACM Transactions on Graphics, vol. 33, no. 2, ACM, 2014, doi:10.1145/2546276.
short: A. Bermano, D. Bradley, T. Beeler, F. Zund, D. Nowrouzezahrai, I. Baran,
O. Sorkine Hornung, H. Pfister, R. Sumner, B. Bickel, M. Groß, ACM Transactions
on Graphics 33 (2014).
date_created: 2018-12-11T11:55:48Z
date_published: 2014-03-01T00:00:00Z
date_updated: 2021-01-12T06:55:24Z
day: '01'
doi: 10.1145/2546276
extern: 1
intvolume: ' 33'
issue: '2'
month: '03'
publication: ACM Transactions on Graphics
publication_status: published
publisher: ACM
publist_id: '4919'
quality_controlled: 0
status: public
title: Facial performance enhancement using dynamic shape space analysis
type: journal_article
volume: 33
year: '2014'
...