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
- Files:
-
-
(Preview, Accepted manuscript, pdf, 7.1MB, Terms of use)
-
Authors
- 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
- Copyright holder:
- Association for Computing Machinery
- Copyright date:
- 2016
- Notes:
- © 2016 Association for Computing Machinery. This is the accepted manuscript version of the article. The final version is available online from the Association for Computing Machinery at: https://dl.acm.org/citation.cfm?id=3045533
If you are the owner of this record, you can report an update to it here: Report update to this record