TY - GEN
T1 - A fully automatic framework for building 3D animated avatars
AU - Boujut, Hugo
AU - Ourir, Mejdi
AU - Zaharia, Titus
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2015/2/5
Y1 - 2015/2/5
N2 - The face animation process still requires an important amount of manual human interaction involving highly qualified artists with strong knowledge in facial anatomy. In this paper, we introduce a framework for automatic construction of 3D animated avatars. The proposed approach allows for animating an inanimate facial 3D mesh. The adopted representation is based on the MPEG-4 standard. First, the Supervised Descent Method (SDM) is employed for detecting automatically the MPEG-4 feature points starting from 2D images consisting of projections of 3D avatars. The originality of the approach consists of the training procedure proposed. Thus, we specifically train a SDM detector for each part of the face, i.e. mouth, eyes, nose, chin, cheeks, etc. Skinning operations are performed by jointly using the MPEG-4 FAPs and the feature point based deformation method. The combination of these three methods allows for building animated avatar with a large variety of shapes, i.e. from realistic human faces to cartoons.
AB - The face animation process still requires an important amount of manual human interaction involving highly qualified artists with strong knowledge in facial anatomy. In this paper, we introduce a framework for automatic construction of 3D animated avatars. The proposed approach allows for animating an inanimate facial 3D mesh. The adopted representation is based on the MPEG-4 standard. First, the Supervised Descent Method (SDM) is employed for detecting automatically the MPEG-4 feature points starting from 2D images consisting of projections of 3D avatars. The originality of the approach consists of the training procedure proposed. Thus, we specifically train a SDM detector for each part of the face, i.e. mouth, eyes, nose, chin, cheeks, etc. Skinning operations are performed by jointly using the MPEG-4 FAPs and the feature point based deformation method. The combination of these three methods allows for building animated avatar with a large variety of shapes, i.e. from realistic human faces to cartoons.
KW - 3D avatar animation
KW - MPEG-4 FAPs
KW - SIFT
KW - Supervised Descent Method
U2 - 10.1109/ICCE-Berlin.2014.7034312
DO - 10.1109/ICCE-Berlin.2014.7034312
M3 - Conference contribution
AN - SCOPUS:84937931357
T3 - IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
SP - 36
EP - 40
BT - Proceedings 2014 IEEE 4th International Conference on Consumer Electronics - Berlin, ICCE-Berlin
A2 - Bellido, Francisco J.
A2 - Hepper, Dietmar
A2 - Cycon, Hans L.
A2 - Huhn, Alexander
PB - IEEE Computer Society
T2 - 2014 4th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
Y2 - 7 September 2014 through 10 September 2014
ER -