Arbitrary image stylization is an algorithm that has been trained to be able to break down any image to stylize another image. With the use of this model https://github.com/reiinakano/arbitrary-image-stylization-tfjs I have applied this to 3d objects. By using a randomization factor and a random pattern the result becomes unique for every new stylization. Written in Javascript with the use of
Make sure you have the following installed:
Clone the repository:
git clone https://github.com/Matthias-VdC/iot-ai-werkstuk-matthias/
cd iot-ai-werkstuk-matthias
Update to the latest commit:
git pull
Install all dependencies:
npm install
Run project:
npm start
https://learn.ml5js.org/#/reference/style-transfer
https://threejs.org/
https://stackoverflow.com/questions/56660584/how-to-override-gltf-materials-in-three-js
https://www.youtube.com/watch?v=e_WC3b5Hy8Q
https://www.vecteezy.com/photo/2317574-empty-brick-wall-with-blue-and-pink-neon-light
https://css-tricks.com/how-to-create-neon-text-with-css/
https://getbootstrap.com/
https://www.tensorflow.org/hub/tutorials/tf2_arbitrary_image_stylization
https://github.com/tensorflow/models/blob/master/research/nst_blogpost/4_Neural_Style_Transfer_with_Eager_Execution.ipynb
https://www.youtube.com/watch?v=dMq4nAMuqO8&list=PL3OV2Akk7XpDmz2oSyTv6AOtOtDZwC2ee
https://www.youtube.com/watch?v=STHRNIJc-vI
https://www.tensorflow.org/js