Learning to Generate Chairs With Convolutional Neural Networks

Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1538-1546

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Dosovitskiy_2015_CVPR,
author = {Dosovitskiy, Alexey and Tobias Springenberg, Jost and Brox, Thomas},
title = {Learning to Generate Chairs With Convolutional Neural Networks},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}