bryandlee's github has the results of image translation application using deep generative model and related research made into a specific webtoon style comic picture as known as "the cool guy". The title of the study is also “Cool Generative Model Learner”. I like this naming!
Looking at the process, 500 webtoon cuts were fed into the face position recognizer but it didn't work well, so he cuts out the face manually, and if the resolution is too low, the picture were upsampled with the super resolution technology to 256x256 sizes.
The learning data created in this way was applied in various ways such as StyleGAN, U-GAT-IT, and latent space exploration. It looks so good to calmly overcome the difficulties experienced in the middle of the research process. The links below are two github links that explain the process above.
