We introduce a convolutional neural network for inferring a compact disentangled graphical description of objects from 2D images that can be used for volumetric reconstruction. The network comprises an encoder and a twin-tailed decoder. The encoder generates a disentangled graphics code. The first decoder generates a volume, and the second decoder reconstructs the input image using a novel training regime that allows the graphics code to learn a separate representation of the 3D object and a description of its lighting and pose conditions. We demonstrate this method by generating volumes and disentangled graphical descriptions from images and videos of faces and chairs.
@article{arxiv.1610.03777,
title = {Deep disentangled representations for volumetric reconstruction},
author = {Edward Grant and Pushmeet Kohli and Marcel van Gerven},
journal= {arXiv preprint arXiv:1610.03777},
year = {2016}
}