3D Morphable Models as Spatial Transformer Networks

Autor:	Bas, Anil, Huber, Patrik, Smith, William A. P., Awais, Muhammad, Kittler, Josef
Rok vydání:	2017
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning 68T45 I.4.8 I.2.10
Druh dokumentu:	Working Paper
DOI:	10.1109/ICCVW.2017.110
Popis:	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. Comment: Accepted to ICCV 2017 2nd Workshop on Geometry Meets Deep Learning
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1708.07199 Zobrazit plný text záznamu View this record from Arxiv