Naive Background Style Transfer implemented using Keras and TensorFlow by Vikram Shenoy.
Naive background style transfer performs style transfer only on the background of the given content image. This naive approach uses two networks to reproduce this style transfer. The DeepLabv3+ model generates a segmentation map of the image which is processed to create a binary mask highlighting the foreground from the background. The style transfer model uses this segmented mask to guide the stylized pixels only onto the background of the given content image. For more details, check out the report.
The above architecture shows how the algorithm works and creates the resulting output image.
The picture below is of me taken on my trip to Amsterdam.
The picture displayed here is the result of Naive Background Style Transfer in the style of one of my favorite pieces of art, The Starry Night by Vincent Van Gogh.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
For using Naive Background Style Transfer, you need to install Keras, TensorFlow, PIL, and Imageio.
pip install keras
pip install tensorflow
pip install Pillow
pip install imageio
| Content Image | Style Image |
|---|---|
 |
 |
Run the script main.py in the terminal as follows.
Python main.py
The final output is stored in Output Images.
Here is the generated image through different intervals of the run.
This section takes a closer look at the hyperparameters of NBST, mainly the content weight and the style weight.
• Content Weight = 1e3
• Style Weight = 1e-2
• Content Weight = 1e10
• Style Weight = 1e-2
• Content Weight = 1e3
• Style Weight = 1e15
- Keras - Deep Learning Framework
- TensorFlow - Deep Learning Framework
- Google Colab - Cloud Service
- Vikram Shenoy - Initial work - Vikram Shenoy
- Leon A. Gatys's paper, A Neural Algorithm of Artistic Style
- Liang-Chieh Chen's paper, Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- Project makes use of the Pre-trained DeepLabv3+ Model by Google
- Content Image: Scraped from Google Image Search, Aila Images
- Style Image: The Scream by Edvard Munch, The Scream
- Style Image: Starry Night by Vincent Van Gogh, The Starry Night