INTERACTIVE STYLE TRANSFER FOR DATA VISUALIZATION AND DATA ART

Data Brushes is an interactive web application to explore neural style transfer using models trained on artistic data visualizations. The application invites casual creators to engage with deep convolutional neural networks to co-create custom artworks with a focus on style transfer networks created from canonical and contemporary works of data visualization and data art to demonstrate the versatility and flexibility of the algorithm. In addition to enabling a novel creative workflow, the process of interactively modifying an image via multiple style transfer networks reveals meaningful features encoded within the networks, and provides insight into the effects particular networks have on different images, or different regions within a single image.

The project explores both the practical uses of such tools for artists as Data Brushes and the interpretive uses of creating such venues for accessibility to computational art, remixing the purpose of data visualizations to be more than just graphical representations of information. Access the project Github page here, and use the buttons below to read the full thesis and paper, as well as explore the UCSC Creative Coding Lab and IEEE VIS Arts Program.

Text on this page is adapted from my UCSC Masters thesis & the full paper published and presented at IEEE VIS 2019 in Vancouver, BC, Canada.