Multilinear pose and body shape estimation of dressed subjects from image sets

In this paper we propose a multilinear model of human pose and body shape which is estimated from a database of registered 3D body scans in different poses. The model is generated by factorizing the measurements into pose and shape dependent components. By combining it with an ICP based registration...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 1823 - 1830
Main Authors Hasler, N, Ackermann, H, Rosenhahn, B, Thormählen, T, Seidel, H
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2010
Subjects
Animation
Biological system modeling
Calibration
Cameras
Deformable models
Humans
Image databases
Pipelines
Shape measurement
Skeleton
Online AccessGet full text

Cover

More Information
Summary:In this paper we propose a multilinear model of human pose and body shape which is estimated from a database of registered 3D body scans in different poses. The model is generated by factorizing the measurements into pose and shape dependent components. By combining it with an ICP based registration method, we are able to estimate pose and body shape of dressed subjects from single images. If several images of the subject are available, shape and poses can be optimized simultaneously for all input images. Additionally, while estimating pose and shape, we use the model as a virtual calibration pattern and also recover the parameters of the perspective camera model the images were created with.
ISBN:1424469848
9781424469840
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2010.5539853