Symmetric shape morphing and symmetry-factored shape modelling

Hang Dai, Nick Pears, Will Smith, Department of Computer Science, University of York, UK

Christian Duncan, Alder Hey Craniofacial Unit, Liverpool, UK

We have applied both symmetric morphing [1] and symmetry-factored modelling [2] to our 3D Morphable Modelling pipeline and demonstrated its effectiveness on the performance of 3D Morphable Models (3DMMs) of the human head.

The image below shows robustness of our symmetric morphing to typical 3D image artefacts

The image below shows the mean head shape and the first 5 principal components of symmetric head shape variation


Symmetric variations in head shape

Asymmetric variations in head shape


  1. Symmetric Shape Morphing for 3D Face and Head Modelling
      H. Dai, N. E. Pears, W. Smith and C. Duncan
      Proc. 2018 IEEE Int. Conf. Automatic Face and Gesture Recognition (FG 2018 oral presentation) pp. 91-97

  2. Symmetry-factored Statistical Modelling of Craniofacial Shape
      H. Dai, W. Smith, N. E. Pears, and C. Duncan
      Proc. 2017 PeopleCap Workshop, Int. Conf. Computer Vision (ICCV 2017) pp. 786-794

Project sponsors

We thank

BACK to Nick Pears' Research Projects page.