Conference item icon

Conference item

Texture networks: Feed-forward synthesis of textures and stylized images

Abstract:
Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example. However, their methods require a slow and memoryconsuming optimization process. We propose here an alternative approach that moves the computational burden to a learning stage. Given a single example of a texture, our approach trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer artistic style from a given image to any other image. The resulting networks are remarkably light-weight and can generate textures of quality comparable to Gatys et al., but hundreds of times faster. More generally, our approach highlights the power and flexibility of generative feed-forward models trained with complex and expressive loss functions.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author


Publisher:
Association for Computing Machinery
Host title:
33rd International Conference on Machine Learning (ICML 2016)
Journal:
33rd International Conference on Machine Learning (ICML 2016) More from this journal
Publication date:
2016-06-19
Acceptance date:
2016-04-24
ISBN:
9781510829008


Pubs id:
pubs:666864
UUID:
uuid:76d0f6d6-00f4-4c9b-a6a8-b12c2e68b1a7
Local pid:
pubs:666864
Source identifiers:
666864
Deposit date:
2018-11-26
ARK identifier:

Terms of use


Views and Downloads

Views and downloads will return soon






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP