AI Abstracts

Abstract Portraits using computational AI

Work in Progress using new software that uses Deep Neural Networks (AI) to abstract a source portrait sitter image using our software.

Teaching a computer algorithm to create an aesthetic abstraction is an unknown- what makes an abstraction hold the aesthetic of a fully detailed painting or sitter image?

Self Portrait Series: AI based abstraction series. Travis Portrait: AI based abstraction series. Self Portrait Series: AI based abstraction series. Dance AI dance abstract video


AI, GeneticProg, Creativity, GenerativeDesign

Evolving Portraits

Genetic Programing to Evolve Portraits

A conceptual piece that evolves a related family of abstract portrait painters. Portraits are created by Darwinian evolution using the AI programming technique called Genetic Programming. Using the painting of Darwin by John Collier as the creative spark (the evolutionary resemblance test they survive by), portraits slowly evolve over a month of constant computer time in this art programming experiment to cajole a computer to become creative on its own (see paper). The mathematical genes were not specifically created for the portrait painting task, but were our genes any different -- surely not originally created for writing computer programs or making art.

Can you bring the ghost (creativity) out of the machine (the computer) using the ghost of Darwin (his namesake techniques and portrait).

Touring exhibition: MIT Museum :: Cambridge University's King Art Centre :: Tenderpixel Gallery, London.

Programming, concepts and art: Steve DiPaola

Darwin portraits: All these abstract portraits (selected from 100's) evolved from the Darwin sitter image (1) and are alive and are related (one family tree). Earlylate: The source image and early evolved portraits in the first row with later more complex (more evolved) portraits in the second row (selected - see link for more). Breeding: Portraits are alive (the genes of every painting are saved), so it is possible to recombine any, like these two & create new offspring (note how offspring combine painterly strategies of the parents)


AI, GeneticProg, Creativity, GenerativeDesign

Selected Stills III

Photographs and Liteboxes 2000-2004

Selected large framed work or liteboxes portraits created via 3D systems (mostly artist's original programs) and typically realized on photography media. The work has been exhibited internationally - mostly in galleries in NYC and California.

Series III : 3D painterly noise series - experiments in 'brush strokes abstract space rather than color'.

Noise 53a: More recent stochastic noise perturbation experiments.  History: A.I.R. Gallery, NYC, 2004. Sold. Noise 59a: More recent stochastic noise perturbation experiments.  History: Times Up Gallery Space, NYC.


Selected Stills II

Photographs and Liteboxes 1990-1995

Selected large framed work or liteboxes portraits created via 3D systems (mostly artist's original programs) and typically realized on photography media. The work has been exhibited internationally - mostly in galleries in NYC and California.

SeriesII : 3D stochastic noise series.

Three muses: Created from my first experiments in using 3D stochastic noise (noise code by John Lewis) at NYIT. The background is created from the foreground objects. History: Times Up Gallery Space, NYC. States of mind III: cibrachrome transparency lightbox. Homage to Boccioni.  History: Tibor De Nagy Gallery, NYC. Pedestal: Cibrachrome Print.


Selected Stills I

Photographs and Liteboxes 1987-1991

Selected large framed work or liteboxes portraits created via 3D systems (mostly artist's original programs) and typically realized on photography media. The work has been exhibited internationally - mostly in galleries in NYC and California.

Series I : Wolfgang and Ralf series - members of Kraftwerk allowed me to use their digital faces I created for them in my own abstract figurative art work.

Ralf2: Cibrachrome print - inspired by Kraftwerk work. History: Times Up Gallery Space, NYC. Blue cirque: Cibrachrome print - inspired by Kraftwerk work. History: Tibor De Nagy Gallery NYC. Claire de lune: Cibrachrome transparency lightbox. History: Tibor De Nagy Gallery NYC, Tapestry Group Show, Herbst Theater, San Francisco. Montage: Private Collection.


Revisting Rembrandt

Rembrandt's Textural Agency / Vision Science Work

Using new visual computer modelling techniques, we show that artists use vision based techniques (lost and found edges, center of focus techniques) to guide the eye path of the viewer through their paintings in significant ways. These methods are known but have rarely been proven; even so, they typically are considered modern painting techniques. We have research that hypothesizes that Rembrandt, reacting to his Italian contemporaries, may have been the first to fully develop these specific painterly techniques, ones that are typically not associated with the early modern period — that engage the viewer and direct their gaze. Did artists like Rembrandt intuit a certain understanding of vision science (central visioning) that scientists only fully understood centuries later? New data from scientific eye tracking studies appear to show how Rembrandt's late portraits exhibit strong use of vision based techniques.


Creativity, Vision, CogSci, PainterlyRendering