A Multilinear Model for Bidirectional Craniofacial Reconstruction

Abstract

We present a bidirectional facial reconstruction method for estimating the skull given a scan of the skin surface and vice versa estimating the skin surface given the skull. Our approach is based on a multilinear model that describes the correlation between the skull and the facial soft tissue thickness (FSTT) on the one hand and the head/face surface geometry on the other hand. Training this model requires to densely sample the Cartesian product space of skull shape times FSTT variation, which cannot be obtained by measurements alone. We generate this data by enriching measured data—volumetric computed tomography scans and 3D surface scans of the head—by simulating statistically plausible FSTT variations. We demonstrate the versatility of our novel multilinear model by estimating faces from given skulls as well as skulls from given faces within just a couple of seconds. To foster further research in this direction, we will make our multilinear model publicly available.

Demo Application

The following application (takes a while to load/start and) showcases a subset of the multilinear model, using seven parameters for skull shapes and four parameters for the facial soft tissue thickness. The multilinear model and source code for this application can be downloaded here and on github.

Related Publications:

[1]	A Multilinear Model for Bidirectional Craniofacial Reconstruction Jascha Achenbach, Robert Brylka, Thomas Gietzen, Katja zum Hebel, Elmar Schömer, Ralf Schulze, Mario Botsch, Ulrich Schwanecke Proceedings of Eurographics Workshop on Visual Computing for Biology and Medicine, 2018, pp. 67-76. Paper Data Code
[2]	A method for automatic forensic facial reconstruction based on dense statistics of soft tissue thickness Thomas Gietzen, Robert Brylka, Jascha Achenbach, Katja zum Hebel, Elmar Schömer, Mario Botsch, Ulrich Schwanecke, Ralf Schulze PLoS ONE, 14(1), 2019. Publisher