Computationally Rendered Painterly Portrait Spaces
Steve DiPaola: Computationally Rendered Painterly Portrait Spaces. Artciencia: Art & Science Journal, Vol 4, No 9, pp 1-8, October-January, 2008.
Is it possible to computationally model the open methodology that fine art portrait painters have used for centuries, into a computer system? A computational system which is capable of producing creative art work on its own from sitter photographs and in doing have a interdisciplinary toolkit that artists, scientists and critics can use to understand and explore the creative artistic process?
This work is ongoing output from research work by Steve DiPaola that attempts to build a computational painting system (called ‘painterly’) that allows aspects of art (the creative human act of fine art painting) and science (cognition, vision and perception; as well as computational design) to both enhance and validate each other. The research takes a novel approach to non photorealistic rendering (NPR) which relies on parameterizing a semantic knowledge space of how a human painter paints, that is, the creative and cognitive process. This approach has two significant benefits and therefore two intertwining and interdisciplinary research outcomes. The first benefit is creating a new type of painterly NPR system with both a wider range and improved results compared to current techniques. The second benefit, is that portrait artists over 1000’s of years have somewhat intuitively evolved a ‘painting methodology’ which exploits specific human vision and cognitive (neural) functions, and therefore when presented in a quantitative way (from our system) can shed light on psychological research in human vision and perception (or at least validate it via another method). The reverse is also true - via this system and process, cognitive scientists can understand artistic technique (which can be useful in many areas including how to make design systems creative).