Imperial College London
Alternate

STEFANOS ZAFEIRIOU, PhD

Faculty of Engineering, Department of Computing

Professor in Machine Learning & Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8461s.zafeiriou Website CV

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Booth:2018:10.1109/TPAMI.2018.2832138,
author = {Booth, J and Roussos, A and Ververas, E and Antonakos, E and Poumpis, S and Panagakis, Y and Zafeiriou, SP},
doi = {10.1109/TPAMI.2018.2832138},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages = {2638--2652},
title = {3D reconstruction of "in-the-wild" faces in images and videos},
url = {http://dx.doi.org/10.1109/TPAMI.2018.2832138},
volume = {40},
year = {2018}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 3D Morphable Models (3DMMs) are powerful statistical models of 3D facial shape and texture, and among the state-of-the-art methods for reconstructing facial shape from single images. With the advent of new 3D sensors, many 3D facial datasets have been collected containing both neutral as well as expressive faces. However, all datasets are captured under controlled conditions. Thus, even though powerful 3D facial shape models can be learnt from such data, it is difficult to build statistical texture models that are sufficient to reconstruct faces captured in unconstrained conditions ("in-the-wild"). In this paper, we propose the first "in-the-wild" 3DMM by combining a statistical model of facial identity and expression shape with an "in-the-wild" texture model. We show that such an approach allows for the development of a greatly simplified fitting procedure for images and videos, as there is no need to optimise with regards to the illumination parameters. We have collected three new databases that combine "in-the-wild" images and video with ground truth 3D facial geometry, the first of their kind, and report extensive quantitative evaluations using them that demonstrate our method is state-of-the-art.
AU  - Booth,J
AU  - Roussos,A
AU  - Ververas,E
AU  - Antonakos,E
AU  - Poumpis,S
AU  - Panagakis,Y
AU  - Zafeiriou,SP
DO  - 10.1109/TPAMI.2018.2832138
EP  - 2652
PY  - 2018///
SN  - 0162-8828
SP  - 2638
TI  - 3D reconstruction of "in-the-wild" faces in images and videos
T2  - IEEE Transactions on Pattern Analysis and Machine Intelligence
UR  - http://dx.doi.org/10.1109/TPAMI.2018.2832138
UR  - https://www.ncbi.nlm.nih.gov/pubmed/29993707
UR  - http://hdl.handle.net/10044/1/83711
VL  - 40
ER  -
Download