The Community for Technology Leaders
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Boston, MA, USA
June 7, 2015 to June 12, 2015
ISSN: 1063-6919
ISBN: 978-1-4673-6963-3
pp: 1538-1546
Alexey Dosovitskiy , Department of Computer Science, University of Freiburg, Germany
Jost Tobias Springenberg , Department of Computer Science, University of Freiburg, Germany
Thomas Brox , Department of Computer Science, University of Freiburg, Germany
ABSTRACT
We train a generative convolutional neural network which is able to generate images of objects given object type, viewpoint, and color. We train the network in a supervised manner on a dataset of rendered 3D chair models. Our experiments show that the network does not merely learn all images by heart, but rather finds a meaningful representation of a 3D chair model allowing it to assess the similarity of different chairs, interpolate between given viewpoints to generate the missing ones, or invent new chair styles by interpolating between chairs from the training set. We show that the network can be used to find correspondences between different chairs from the dataset, outperforming existing approaches on this task.
INDEX TERMS
CITATION

A. Dosovitskiy, J. T. Springenberg and T. Brox, "Learning to generate chairs with convolutional neural networks," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 1538-1546.
doi:10.1109/CVPR.2015.7298761
184 ms
(Ver 3.3 (11022016))