Techniques of the Master Painter

Reference photo. All images from Gurney Journey, though
some originated in this article.

Blobby Photoshop "artist filter" adaptation

Master painting

James Gurney, author/artist behind the book series Dinotopia, who, among other things is an excellent plein air painter and very knowledgeable about technique, has a really interesting post about "image parsing" at his main blog, Gurney Journey. The thrust of the post is that:

Machines like Vangobot may develop the hand skills to manipulate the brushes and paints, but will they ever have artistic judgment? Is it possible for a computer to be programmed to see and interpret the world in the same way that an experienced painter does?

These are qualities of the "eye" or "mind" or even the "soul" more than the "hand." Blog reader M.P. invoked a quote from nineteenth century drawing instructor James Duffield Harding who characterized the great artist as having an instinct for "selection, arrangement, sentiment, and beauty" rather than just replicating reality.

      * * *
Note the difference in this master painter's interpretation. The details in the faces are accurately drawn, but rougher brushes are used for the foliage. The drapery is painted efficiently with big slashing strokes. The sky is painted loosely with spots of light. The sidewalk tiles are in perspective, but they're just suggested with thin dashing strokes. The colors are warmed up and intensified.

For a computer to do this, it would have to understand what it was looking at, and have an instinct to do all these subjective interpretations. It would need to be able to handle a lot of brushes in a variety of ways depending on what forms it was painting.

He's toying with us.

Now what if I told you that the "master painter" of all of the examples is a computer?

The creators of the program are Kun Zeng, Mingtian Zhao, Caiming Xiong, Song-Chun Zhu from Lotus Hill Institute and University of California, Los Angeles. The goal for the software was to interpret photographs in painterly terms.

      * * *
The process begins with "image parsing," where the scene is divided and grouped into various areas of unequal importance and of unequal character, such as foliage, branches, drapery, and faces. Each region of the painting has different meaning to a viewer and therefore requires a different paint handling. This visual meaning is known in the field of artificial intelligence as "image semantics."

Gurney goes on to describe how the computer parses the field in some detail with several nice supporting images (some from Zeng et al.'s article Gurney refers to). 

The "master painting" offered by Gurney and Zeng et al. is not really a master work but a very nice illustration. And what it illustrates is not just a scene (a scene that was selected by people by the way, not the computer ... though I am not sure why eventually a computer could not be programmed to pick or design an appropriate scene); it illustrates that computers and technology are encroaching on the heretofore supposedly uniquely human practice of art. That's been true since the advent of photography, of course, and the broader acceptance of abstraction in fine art has been, in part, a response to that. 

I would suggest that artists who want to pursue their work as more than just a hobby are going to have to find ways, eventually, to show that their work was made by a human and not a machine. And those that can will be able to sell their work for a premium.