Learning to Generate Chairs, Tables and Cars with Convolutional Networks
Learning to Generate Chairs, Tables and Cars with Convolutional Networks
复制标题
DOI：
10.1109/tpami.2016.2567384
复制
发表时间：
2017-04-01
影响因子：
23.6
通讯作者：
Brox, Thomas
中科院分区：
文献类型：
--
作者：
Dosovitskiy, Alexey;Springenberg, Jost Tobias;Brox, Thomas
我们训练生成的“上卷积”神经网络，它能够生成给定对象样式、视点和颜色的对象图像。我们在椅子、桌子和汽车的渲染3D模型上训练网络。我们的实验表明，这些网络不仅仅是用心学习所有图像，而是找到一种有意义的3D模型表示，使它们能够评估不同模型的相似性，在给定视图之间进行插值以生成缺失的视图，外推视图，并通过重组训练实例，甚至两个不同的对象类来发明训练集中不存在的新对象。此外，我们还证明了这种生成网络可以用于从数据集中找到不同对象之间的对应关系，在这一任务上优于现有方法。
We train generative "up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color. We train the networks on rendered 3D models of chairs, tables, and cars. Our experiments show that the networks do not merely learn all images by heart, but rather find a meaningful representation of 3D models allowing them to assess the similarity of different models, interpolate between given views to generate the missing ones, extrapolate views, and invent new objects not present in the training set by recombining training instances, or even two different object classes. Moreover, we show that such generative networks can be used to find correspondences between different objects from the dataset, outperforming existing approaches on this task.