Imperial College London


Faculty of EngineeringDepartment of Computing

Professor in Machine Learning & Computer Vision



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




375Huxley BuildingSouth Kensington Campus






BibTex format

author = {Ploumpis, S and Wang, H and Pears, N and Smith, W and Zafeiriou, S},
publisher = {IEEE},
title = {Combining 3D morphable models: a large-scale face-and-head model},
url = {},
year = {2019}

RIS format (EndNote, RefMan)

AB - Three-dimensional Morphable Models (3DMMs) arepowerful statistical tools for representing the 3D surfacesof an object class. In this context, we identify an interestingquestion that has previously not received research attention:is it possible to combine two or more 3DMMs that (a) arebuilt using different templates that perhaps only partly overlap,(b) have different representation capabilities and (c)are built from different datasets that may not be publiclyavailable?In answering this question, we make two contributions.First, we propose two methods for solving thisproblem: i. use a regressor to complete missing parts ofone model using the other, ii. use the Gaussian Processframework to blend covariance matrices from multiple models.Second, as an example application of our approach,we build a new face-and-head shape model that combinesthe variability and facial detail of the LSFM with the fullhead modelling of the LYHM. The resulting combined shapemodel achieves state-of-the-art performance and outperformsexisting head models by a large margin. Finally, as anapplication experiment, we reconstruct full head representationsfrom single, unconstrained images by utilizing ourproposed large-scale model in conjunction with the Face-Warehouse blendshapes for handling expressions.
AU - Ploumpis,S
AU - Wang,H
AU - Pears,N
AU - Smith,W
AU - Zafeiriou,S
PY - 2019///
TI - Combining 3D morphable models: a large-scale face-and-head model
UR -
ER -