Data-driven Digital Drawing and Painting

Abstract

Digital artists create evocative drawings and paintings using a tablet and stylus coupled with digital painting software. Research systems have shown promising improvements in various aspects of the art creation process by targeting specific drawing styles and natural media, for example oil paint or watercolor. They combine carefully hand-crafted procedural rules and computationally

expensive, style-specific physical simulations. Nevertheless, untrained users often find it hard to achieve their target style in these systems due to the challenge of controlling and predicting the outcome of their collective drawing strokes. Moreover even trained digital artists are often restricted by the inherent stylistic limitations of these systems.

In this thesis, we propose a data-driven painting paradigm that allows novices and experts to more easily create visually compelling artworks using exemplars. To make data-driven painting feasible and efficient, we factorize the painting process into a set of orthogonal components: 1) stroke paths; 2) hand gestures; 3) stroke textures; 4) inter-stroke interactions; 5) pigment colors. We present four prototype systems, HelpingHand, RealBrush, DecoBrush and RealPigment, to demonstrate that each component can be synthesized efficiently and independently based on small sets of decoupled exemplars. We propose efficient algorithms to acquire and process visual exemplars and a general framework for data-driven stroke synthesis based on feature matching and optimization. With the convenience of data sharing on the Internet, this data-driven paradigm opens up new opportunities for artists and amateurs to create original stylistic artwork and to abstract, share and reproduce their styles more easily and faithfully.