Biblio

Re-drawing the image as a certain artistic style is considered to be a complicated task for computer machine. On the contrary, human can easily master the method to compose and describe the style between different images. In the past, many researchers studying on the deep neural networks had found an appropriate representation of the artistic style using perceptual loss and style reconstruction loss. In the previous works, Gatys et al. proposed an artificial system based on convolutional neural networks that creates artistic images of high perceptual quality. Whereas in terms of running speed, it was relatively time-consuming, thus it cannot apply to video style transfer. Recently, a feed-forward CNN approach has shown the potential of fast style transformation, which is an end-to-end system without hundreds of iteration while transferring. We combined the benefits of both approaches, optimized the feed-forward network and defined time loss function to make it possible to implement the style transfer on video in real time. In contrast to the past method, our method runs in real time with higher resolution while creating competitive visually pleasing and temporally consistent experimental results.

In this paper, we present initial work towards creating an intelligent interface that can act as an open access laboratory for visual stylometry called WAIVS, Workflows for Analysis of Images and Visual Stylometry. WAIVS allows scholars, students, and other interested parties to explore the nature of artistic style using cutting-edge research methods in visual stylometry. We create semantic workflows for this interface using various computer vision algorithms that not only facilitate artistically significant analyses but also impose intelligent semantic constraints on complex analyses. In the interface, we combine these workflows with a manually-curated dataset for analysis of artistic style based on either the school of art or the medium.