Multilinear Modelling of Faces and Expressions

In this work, we present a new versatile 3D multilinear statistical face model, based on a tensor factorisation of 3D face scans, that decomposes the shapes into person and expression subspaces. Investigation of the expression subspace reveals an inherent low-dimensional substructure, and further, a...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 10 vom: 30. Okt., Seite 3540-3554
1. Verfasser: Grasshof, Stella (VerfasserIn)
Weitere Verfasser: Ackermann, Hanno, Brandt, Sami Sebastian, Ostermann, Jorn
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2021
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM308906802
003 DE-627
005 20231225132739.0
007 cr uuu---uuuuu
008 231225s2021 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2020.2986496  |2 doi 
028 5 2 |a pubmed24n1029.xml 
035 |a (DE-627)NLM308906802 
035 |a (NLM)32305893 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Grasshof, Stella  |e verfasserin  |4 aut 
245 1 0 |a Multilinear Modelling of Faces and Expressions 
264 1 |c 2021 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 10.12.2021 
500 |a Date Revised 14.12.2021 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a In this work, we present a new versatile 3D multilinear statistical face model, based on a tensor factorisation of 3D face scans, that decomposes the shapes into person and expression subspaces. Investigation of the expression subspace reveals an inherent low-dimensional substructure, and further, a star-shaped structure. This is due to two novel findings. (1) Increasing the strength of one emotion approximately forms a linear trajectory in the subspace. (2) All these trajectories intersect at a single point - not at the neutral expression as assumed by almost all prior works-but at an apathetic expression. We utilise these structural findings by reparameterising the expression subspace by the fourth-order moment tensor centred at the point of apathy. We propose a 3D face reconstruction method from single or multiple 2D projections by assuming an uncalibrated projective camera model. The non-linearity caused by the perspective projection can be neatly included into the model. The proposed algorithm separates person and expression subspaces convincingly, and enables flexible, natural modelling of expressions for a wide variety of human faces. Applying the method on independent faces showed that morphing between different persons and expressions can be performed without strong deformations 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Ackermann, Hanno  |e verfasserin  |4 aut 
700 1 |a Brandt, Sami Sebastian  |e verfasserin  |4 aut 
700 1 |a Ostermann, Jorn  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 43(2021), 10 vom: 30. Okt., Seite 3540-3554  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:43  |g year:2021  |g number:10  |g day:30  |g month:10  |g pages:3540-3554 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2020.2986496  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 43  |j 2021  |e 10  |b 30  |c 10  |h 3540-3554