3D Morphable Models as Spatial Transformer Networks
release_adrjbaxnybde7oxq4qy7qj5gjm
by
Anil Bas, Patrik Huber, William A. P. Smith, Muhammad Awais, Josef
Kittler
2017
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.
In text/plain
format
Archived Files and Locations
application/pdf 1.2 MB
file_7hkpnpawlfc5znfqo623ulfo4a
|
arxiv.org (repository) web.archive.org (webarchive) |
1708.07199v1
access all versions, variants, and formats of this works (eg, pre-prints)