Data-driven Digital Drawing and Painting
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 specic
drawing styles and natural media, for example oil paint or watercolor. They combine carefully hand-crafted procedural rules and computationally expensive, style-specic physical simulations. Nevertheless, untrained users often nd 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 ecient, 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 eciently and independently based on small sets of decoupled exemplars. We propose ecient 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.