Inspiration
One of the team members studied AI at University of Amsterdam where Dutch art was presented in a creative way using VR, AI and more tech. He was asking how Vangogh will paint Saudi Landscape and
What it does
The model was built with art and love using CNN deep learning which transferring a selected landscape to famous artists works
How we built it
As mentioned, we used Style Transfer with Deep Neural Networks. Style transfer relies on separating the content and style of an image. Given one content image and one style image, we aim to create a new, target image which should contain our desired content and style components:
- objects and their arrangement are similar to that of the content image
- style, colors, and textures are similar to that of the style image
Challenges we ran into
Internet access. Cloud was a good solution.
Accomplishments that we're proud of
The model changed the famous Saudi and Islamic landscape that never ever could be imagined from the original artist. This great advantages of the stat of the art AI features and the cutting edge technology will be enabling the young artists to imagine beyond the limits.
What we learned
New python packages, and new art schools. how we mix those together.
What's next
This model can be used to merge any different arts together. However, we would love to improve the model to make the other way around were famous artists' works can be transferred by using some Saudi Style or Arabic or Islamic Art . Arabic font art for instance.
Built With
- deeplearning
- keras
- python
- pytourch
- styletransfer
- vangogh
Log in or sign up for Devpost to join the conversation.