ITU

Multilinear Modelling of Faces and Expressions

Research output: Journal Article or Conference Article in JournalJournal articleResearchpeer-review

Standard

Multilinear Modelling of Faces and Expressions. / Grasshof, Stella; Ackermann, Hanno; Brandt, Sami Sebastian; Ostermann, Jörn.

In: I E E E Transactions on Pattern Analysis and Machine Intelligence, Vol. 43, No. 10, 2020, p. 3540-3554.

Research output: Journal Article or Conference Article in JournalJournal articleResearchpeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{ac6c20a79ab349f1af1cd5a2c2ef7742,
title = "Multilinear Modelling of Faces and Expressions",
abstract = "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.",
keywords = "Statistical shape model, tensor model, HOSVD, person transfer, expression transfer, 3D-reconstruction",
author = "Stella Grasshof and Hanno Ackermann and Brandt, {Sami Sebastian} and J{\"o}rn Ostermann",
year = "2020",
doi = "10.1109/TPAMI.2020.2986496",
language = "English",
volume = "43",
pages = "3540--3554",
journal = "I E E E Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "Institute of Electrical and Electronics Engineers",
number = "10",

}

RIS

TY - JOUR

T1 - Multilinear Modelling of Faces and Expressions

AU - Grasshof, Stella

AU - Ackermann, Hanno

AU - Brandt, Sami Sebastian

AU - Ostermann, Jörn

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

KW - Statistical shape model

KW - tensor model

KW - HOSVD

KW - person transfer

KW - expression transfer

KW - 3D-reconstruction

U2 - 10.1109/TPAMI.2020.2986496

DO - 10.1109/TPAMI.2020.2986496

M3 - Journal article

VL - 43

SP - 3540

EP - 3554

JO - I E E E Transactions on Pattern Analysis and Machine Intelligence

JF - I E E E Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 10

ER -

ID: 85161206