期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 39, 期 4, 页码 692-705出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2016.2567384
关键词
Convolutional networks; generative models; image generation; up-convolutional networks
资金
- ERC Starting Grant VideoLearn [279401]
- Brain-Links-BrainTools Cluster of Excellence - German Research Foundation [EXC 1086]
- European Research Council (ERC) [279401] Funding Source: European Research Council (ERC)
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据