A Keras implementation of Universal Style Transfer via Feature Transforms by Li et al. The core architecture is an auto-encoder trained to reconstruct from intermediate layers of a pre-trained VGG19 image classification net. Stylization is accomplished by matching the statistics of content/style image features through the Whiten-Color Transform (WCT), which is implemented here using NumPy library. No style images are used for training, and the WCT allows for 'universal' style transfer for arbitrary content/style image pairs.
forked from abhijith97/Universal-Style-Transfer
-
Notifications
You must be signed in to change notification settings - Fork 0
A Keras implementation of Universal Style Transfer via Feature Transforms by Li et al. The core architecture is an auto-encoder trained to reconstruct from intermediate layers of a pre-trained VGG19 image classification net. Stylization is accomplished by matching the statistics of content/style image features through the Whiten-Color Transform …
yasminfemerling/Universal-Style-Transfer
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
A Keras implementation of Universal Style Transfer via Feature Transforms by Li et al. The core architecture is an auto-encoder trained to reconstruct from intermediate layers of a pre-trained VGG19 image classification net. Stylization is accomplished by matching the statistics of content/style image features through the Whiten-Color Transform …
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Python 100.0%