Realistic Head Motion Synthesis for an Image-based Talking Head

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des Sammelwerks2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops
UntertitelFG 2011
Seiten125-130
Seitenumfang6
PublikationsstatusVeröffentlicht - Mai 2011
Veranstaltung2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 - Santa Barbara, CA, USA / Vereinigte Staaten
Dauer: 21 März 201125 März 2011

Publikationsreihe

Name2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

Abstract

In this paper, we present a novel approach to add flexible head motions to talking heads. First, head motion patterns are collected from original recordings. These head motion patterns are recorded video segments with different head motions, like nod and shake. The head motion is synthesized by selecting and concatenating appropriate head motion patterns according to the input text or head motion tags. In order to join these patterns, optical flow based morphing is used to smooth transitions without introducing noticeable discontinuities. Experimental results show that head motion synthesis is realistic, and animations with flexible head motions are rated with a higher average mean opinion score than the ones with repeated head motions.

ASJC Scopus Sachgebiete

Zitieren

Realistic Head Motion Synthesis for an Image-based Talking Head. / Liu, Kang; Ostermann, Joern.
2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops: FG 2011. 2011. S. 125-130 5771384 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Liu, K & Ostermann, J 2011, Realistic Head Motion Synthesis for an Image-based Talking Head. in 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops: FG 2011., 5771384, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, S. 125-130, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, Santa Barbara, CA, USA / Vereinigte Staaten, 21 März 2011. https://doi.org/10.1109/FG.2011.5771384
Liu, K., & Ostermann, J. (2011). Realistic Head Motion Synthesis for an Image-based Talking Head. In 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops: FG 2011 (S. 125-130). Artikel 5771384 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011). https://doi.org/10.1109/FG.2011.5771384
Liu K, Ostermann J. Realistic Head Motion Synthesis for an Image-based Talking Head. in 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops: FG 2011. 2011. S. 125-130. 5771384. (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011). doi: 10.1109/FG.2011.5771384
Liu, Kang ; Ostermann, Joern. / Realistic Head Motion Synthesis for an Image-based Talking Head. 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops: FG 2011. 2011. S. 125-130 (2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011).
Download
@inproceedings{e65e1c142adf4d9b8b526141ff5745e9,
title = "Realistic Head Motion Synthesis for an Image-based Talking Head",
abstract = "In this paper, we present a novel approach to add flexible head motions to talking heads. First, head motion patterns are collected from original recordings. These head motion patterns are recorded video segments with different head motions, like nod and shake. The head motion is synthesized by selecting and concatenating appropriate head motion patterns according to the input text or head motion tags. In order to join these patterns, optical flow based morphing is used to smooth transitions without introducing noticeable discontinuities. Experimental results show that head motion synthesis is realistic, and animations with flexible head motions are rated with a higher average mean opinion score than the ones with repeated head motions.",
author = "Kang Liu and Joern Ostermann",
year = "2011",
month = may,
doi = "10.1109/FG.2011.5771384",
language = "English",
isbn = "9781424491407",
series = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011",
pages = "125--130",
booktitle = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops",
note = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 ; Conference date: 21-03-2011 Through 25-03-2011",

}

Download

TY - GEN

T1 - Realistic Head Motion Synthesis for an Image-based Talking Head

AU - Liu, Kang

AU - Ostermann, Joern

PY - 2011/5

Y1 - 2011/5

N2 - In this paper, we present a novel approach to add flexible head motions to talking heads. First, head motion patterns are collected from original recordings. These head motion patterns are recorded video segments with different head motions, like nod and shake. The head motion is synthesized by selecting and concatenating appropriate head motion patterns according to the input text or head motion tags. In order to join these patterns, optical flow based morphing is used to smooth transitions without introducing noticeable discontinuities. Experimental results show that head motion synthesis is realistic, and animations with flexible head motions are rated with a higher average mean opinion score than the ones with repeated head motions.

AB - In this paper, we present a novel approach to add flexible head motions to talking heads. First, head motion patterns are collected from original recordings. These head motion patterns are recorded video segments with different head motions, like nod and shake. The head motion is synthesized by selecting and concatenating appropriate head motion patterns according to the input text or head motion tags. In order to join these patterns, optical flow based morphing is used to smooth transitions without introducing noticeable discontinuities. Experimental results show that head motion synthesis is realistic, and animations with flexible head motions are rated with a higher average mean opinion score than the ones with repeated head motions.

UR - http://www.scopus.com/inward/record.url?scp=79958749881&partnerID=8YFLogxK

U2 - 10.1109/FG.2011.5771384

DO - 10.1109/FG.2011.5771384

M3 - Conference contribution

AN - SCOPUS:79958749881

SN - 9781424491407

T3 - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

SP - 125

EP - 130

BT - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops

T2 - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

Y2 - 21 March 2011 through 25 March 2011

ER -

Von denselben Autoren