3D Morphable Models as Spatial Transformer Networks

Authors: Bas, A., Huber, P., Smith, W.A.P., Awais, M. and Kittler, J.

Journal: Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

Volume: 2018-January

Pages: 895-903

ISBN: 9781538610343

DOI: 10.1109/ICCVW.2017.110

Abstract:

In this paper, we show how a 3D Morphable Model (i.e. a statistical model of the 3D shape of a class of objects such as faces) can be used to spatially transform input data as a module (a 3DMM-STN) within a convolutional neural network. This is an extension of the original spatial transformer network in that we are able to interpret and normalise 3D pose changes and self-occlusions. The trained localisation part of the network is independently useful since it learns to fit a 3D morphable model to a single image. We show that the localiser can be trained using only simple geometric loss functions on a relatively small dataset yet is able to perform robust normalisation on highly uncontrolled images including occlusion, self-occlusion and large pose changes.

Source: Scopus