Some high-quality resources for you to further dive into the theoretical details of the Neural Style Transfer:
This is the paper Gatys et al. published in 2015, introducing the neural style transfer algorithm for the first time.
This one is the paper Johnson et al. published, in 2016, introducing a more efficient approach to perform neural style transfer.
In case you are not used to reading research papers you can go through the blog posts listed below, as these explain the theoretical details of Neural Style Transfer in a simpler manner.
- Neural Style Transfer: Everything You Need to Know
- A brief introduction to Neural Style Transfer
- How to code Neural Style Transfer in Python
Below is a list of tutorials published at Bleed AI that you can go through to learn everything about the DNN module, including how to train custom classifiers and custom object detectors in TensorFlow and then deploy it in the OpenCV module.
- Deep Learning with OpenCV DNN Module, A Comprehensive Guide
- Training a Custom Image Classifier with Tensorflow, Converting to ONNX, and using it in the OpenCV DNN module
- Using a Custom Trained Object Detector with OpenCV DNN Module
If you have a high-end GPU, you can install OpenCV with GPU Access by going over this tutorial that I had published a while back, note that this tutorial also covers installing Tensorflow 2.0 GPU that you can skip for now.
A Demo video of the self-painting portrait application inspired me to create this application.