Generative Models of Graffiti Form

AutoGraff is a research project aimed at computationally modelling the perceptual and dynamic processes involved in the production of graffiti art and calligraphy. The purpose of the study is to develop computer graphics and robotic systems that are capable of generating traces, letters, and patterns that are similar to the ones made by an expert human artist. The traces and shapes that can be seen in these art forms are often the result of highly skilled and expressive drawing gestures, which require years of practice to master. Similarly, we approach the computational generation of graffiti with a movement centric approach, in which shape results from a dynamic simulation of a movement rather than an explicit definition of its appearence.