The Markov Pen

Online Synthesis of Freehand Drawing Styles

Katrin Lang and Marc Alexa
NPAR 2015


Learning expressive curve styles from example is crucial for interactive or computer-based narrative illustrations. We propose a method for online synthesis of free-hand drawing styles along arbitrary base paths by means of an autoregressive Markov Model. Choice on further curve progression is made while drawing, by sampling from a series of previously learned feature distributions subject to local curvature. The algorithm requires no user- adjustable parameters other than one short example style. It may be used as a custom "random brush" designer in any task that requires rapid placement of a large number of detail-rich shapes that are tedious to create manually.


download paper


Our system learns stylization (blue) as a function of a baseline (green). An analogical style (red) is then applied on a target curve (yellow), while drawing. In doing so, the algorithm accounts for the curvature of the new base path. In the cactus ex- ample (a), for instance, spikes should not be drawn in regions of extreme curvature. In the leaf example (b), the algorithm learns to grow spikes towards the cusps, and in the graffiti example (c), motion lines are placed on locations of high positive curvature.


download video