Deep Convolutional Inverse Graphics Network
Tejas D Kulkarni, William F. Whitney, Pushmeet Kohli, Josh Tenenbaum
Abstract
This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that aims to learn an interpretable representation of images, disentangled with respect to three-dimensional scene structure and viewing transformations such as depth rotations and lighting variations. The DC-IGN model is composed of multiple layers of convolution and de-convolution operators and is trained using the Stochastic Gradient Variational Bayes (SGVB) algorithm. We propose a training procedure to encourage neurons in the graphics code layer to represent a specific transformation (e.g. pose or light). Given a single input image, our model can generate new images of the same object with variations in pose and lighting. We present qualitative and quantitative tests of the model's efficacy at learning a 3D rendering engine for varied object classes including faces and chairs.
BibTeX
@inproceedings{NIPS2015_ced556cd,
author = {Kulkarni, Tejas D and Whitney, William F. and Kohli, Pushmeet and Tenenbaum, Josh},
booktitle = {Advances in Neural Information Processing Systems},
editor = {C. Cortes and N. Lawrence and D. Lee and M. Sugiyama and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Deep Convolutional Inverse Graphics Network},
url = {https://proceedings.neurips.cc/paper_files/paper/2015/file/ced556cd9f9c0c8315cfbe0744a3baf0-Paper.pdf},
volume = {28},
year = {2015}
}