Style Transfer of Black and White Silhouette Images using CycleGAN and a Randomly Generated Dataset
This work addresses style transfer for silhouette images, which is an incremental improvement in a specific domain.
The paper tackled the problem of transferring traditional art style to black and white silhouette images by using CycleGAN trained on randomly generated data, resulting in noticeably better performance than previous neural style transfer methods.
CycleGAN can be used to transfer an artistic style to an image. It does not require pairs of source and stylized images to train a model. Taking this advantage, we propose using randomly generated data to train a machine learning model that can transfer traditional art style to a black and white silhouette image. The result is noticeably better than the previous neural style transfer methods. However, there are some areas for improvement, such as removing artifacts and spikes from the transformed image.