Dynamic Video Face Transformation Using Multilinear and Autoregressive Models

Tiddeman, Bernard; Hunter, David; Perrett, David

Dynamic Video Face Transformation Using Multilinear and Autoregressive Models

Files

049-052.pdf (273.01 KB)

Date

2011

Authors

Tiddeman, Bernard
Hunter, David
Perrett, David

Publisher

The Eurographics Association

Abstract

In this paper we present a prototype system for altering perceived attributes of faces in video sequences, such as the apparent age, sex or emotional state. The system uses multilinear models to decompose the parameters coding for each frame into separate pose and identity parameters. The multilinear model is learnt automatically from the training video data. Statistical models of group identity are then used to alter the identity parameters from one group to another (e.g. from male to female). An autoregressive model is learnt from the pose parameters, and this is applied to alter the dynamics. We have tested our system on a small dataset (for altering apparent gender) with encouraging preliminary results.

        @inproceedings{:10.2312/LocalChapterEvents/TPCG/TPCG11/049-052
,
booktitle = {Theory and Practice of Computer Graphics
},
editor = {Ian Grimstead and Hamish Carr
},
title = {{Dynamic Video Face Transformation Using Multilinear and Autoregressive Models
}},
author = {Tiddeman, Bernard and 
Hunter, David and 
Perrett, David
},
year = {2011
},
publisher = {The Eurographics Association
},
ISBN = {978-3-905673-83-8
},
DOI = {/10.2312/LocalChapterEvents/TPCG/TPCG11/049-052
}
}