Abstract
A method for constructing 3D human facial images which maintains the characteristics of video input image is proposed. First, a personalized 3D polygonal facial model is constructed from two orthogonal facial images. Video input frames are modified, and the vertices composing the 3D polygons are altered according to the contraction rule of facial muscles. Moreover, the modified input frame is texture mapped directly onto to the forementioned model to improve the quality of the reconstructed image. This method was implemented onto an ordinary PC, and an experiment using five persons' face data showed the effectiveness of the method both quantitatively and subjectively.
Original language | English |
---|---|
Title of host publication | Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition |
Pages | 735-742 |
Number of pages | 8 |
DOIs | |
Publication status | Published - 2004 |
Event | Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 - Seoul Duration: 2004 May 17 → 2004 May 19 |
Other
Other | Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 |
---|---|
City | Seoul |
Period | 04/5/17 → 04/5/19 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
Realistic 3D facial animation using parameter-based deformation and texture remapping. / Sato, Hajime; Ohya, Jun; Terashima, Nobuyoshi.
Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition. 2004. p. 735-742.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Realistic 3D facial animation using parameter-based deformation and texture remapping
AU - Sato, Hajime
AU - Ohya, Jun
AU - Terashima, Nobuyoshi
PY - 2004
Y1 - 2004
N2 - A method for constructing 3D human facial images which maintains the characteristics of video input image is proposed. First, a personalized 3D polygonal facial model is constructed from two orthogonal facial images. Video input frames are modified, and the vertices composing the 3D polygons are altered according to the contraction rule of facial muscles. Moreover, the modified input frame is texture mapped directly onto to the forementioned model to improve the quality of the reconstructed image. This method was implemented onto an ordinary PC, and an experiment using five persons' face data showed the effectiveness of the method both quantitatively and subjectively.
AB - A method for constructing 3D human facial images which maintains the characteristics of video input image is proposed. First, a personalized 3D polygonal facial model is constructed from two orthogonal facial images. Video input frames are modified, and the vertices composing the 3D polygons are altered according to the contraction rule of facial muscles. Moreover, the modified input frame is texture mapped directly onto to the forementioned model to improve the quality of the reconstructed image. This method was implemented onto an ordinary PC, and an experiment using five persons' face data showed the effectiveness of the method both quantitatively and subjectively.
UR - http://www.scopus.com/inward/record.url?scp=4544268577&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=4544268577&partnerID=8YFLogxK
U2 - 10.1109/AFGR.2004.1301622
DO - 10.1109/AFGR.2004.1301622
M3 - Conference contribution
AN - SCOPUS:4544268577
SN - 0769521223
SN - 9780769521220
SP - 735
EP - 742
BT - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition
ER -