Photographic painting style transfer using convolutional neural networks

We propose a novel automatic photographic painting style technique with a single example image by using Convolutional Neural Networks (CNN). The photographic painting style is a challenging problem in the research community. Even though, researchers have been trying to obtain good results on painting style, but not much has been done on photographic stylization. Portrait painting techniques are mainly designed for the graphite style and/or are based on image analogies; an example painting as well as its original unpainted version are required. This preceding issue is a motivation of our proposed methods. As a result, our method extends the limits of their domain of applicability. We present a novel multi-convolutional-learning technique that is developed for both images (NPR/PR) labeling, style transmission and elevating a particular unified CNN model per weight sharing. A new painting technique is generated that follows the example style in the example image and maintains the integrity of facial structures. We believe this novel interpretation connects these two important research fields and could enlighten future researches. Moreover, our proposed technique is not restricted to headshot images or specific styles as our method can also change the photographic painting style in the wild.