A Global Optimization Approach to High-detail Reconstruction of the Head

Schneider, David C.; Kettern, Markus; Hilsmann, Anna; Eisert, Peter

A Global Optimization Approach to High-detail Reconstruction of the Head

Files

009-015.pdf (1.17 MB)

Date

2011

Authors

Schneider, David C.
Kettern, Markus
Hilsmann, Anna
Eisert, Peter

Publisher

The Eurographics Association

Abstract

The paper presents an approach for reconstructing head-and-shoulder portraits of people from calibrated stereo images with a high level of geometric detail. In contrast to many existing systems, our reconstructions cover the full head, including hair. This is achieved using a global intensity-based optimization approach which is stated as a parametric warp estimation problem and solved in a robust Gauss-Newton framework. We formulate a computationally efficient warp function for mesh-based estimation of depth which is based on a well known image-registration approach and adapted to the problem of 3D reconstruction. We address the use of sparse correspondence estimates for initializing the optimization as well as a coarse-to-fine scheme for reconstructing without specific initialization. We discuss issues of regularization and brightness constancy violations and show various results to demonstrate the effectiveness of the approach.

        @inproceedings{:10.2312/PE/VMV/VMV11/009-015
,
booktitle = {Vision, Modeling, and Visualization (2011)
},
editor = {Peter Eisert and Joachim Hornegger and Konrad Polthier
},
title = {{A Global Optimization Approach to High-detail Reconstruction of the Head
}},
author = {Schneider, David C. and 
Kettern, Markus and 
Hilsmann, Anna and 
Eisert, Peter
},
year = {2011
},
publisher = {The Eurographics Association
},
ISBN = {978-3-905673-85-2
},
DOI = {/10.2312/PE/VMV/VMV11/009-015
}
}