We submitted some paintings to the robotart contest! Please vote for them (e-David Team Uni Konstanz) if you like them!
Here are pictures of the submitted paintings and descriptions from the submission text from our team page at robotart.org.
The inspiration behind the selfportrait came from a picture that was taken from e-David. We used the perspective of this picture as the only input data four our painting algorithm. All other input, like regions, colors, brush stroke orientations was then chosen from a database we created before. We preselected different stroke patterns and hatchings and implemented the corresponding arm movements. Liat Grayver then used a high level interface that we’ve created specifically for this project to let e-David paint his selfportrait. This language is based on masking regions and selecting one of the predefined variable stroke patterns and freely selectable paint palettes. The final artwork is then no reproduction of a photo – it is an original artwork created as the result of a collaboration between e-David and Liat Grayver.
For the next artwork we also collaborated with Liat Grayver. Liat and us decided to create a painting that combines two styles we recently investigated. One style is based on procedural rules that produce stroke patterns on a 2D Plane, the other one consists of our” traditional” approach that automatically reproduces images using visual feedback and by deriving every parameter like brush stroke orientations, colors and other information directly from the input image. Since we are fans of Jackson Pollock paintings, we decided to pay him homage. We used a famous picture of Pollock painting in his studio as reference and used these two styles for different parts of the painting. First, e-David created two paintings using the procedural approach. We recorded the brush stroke sequence to reuse it later in the other painting. Then we created a 3D Scene of e-David standing in a room resembling the scene of the Pollock picture. We then rendered the scene from a fitting perspective and created lighting, shadow, color and geometric information to derive painting parameters that can be used by the visual feedback algorithm. We distorted the recorded brush strokes of our procedural paintings according to the perspective of our studio scene and painted them on the canvas. By doing so, we have the exact paintings that we’ve generated before, inserted in the final painting.
For the following project we created a painting algorithm that creates abstract stroke patterns by using a combination of random and parameterized functions. Such parameters are for example, Color, brush and step size, orientation, position weights. All of these parameters were varied using Gaussian distribution functions. These parameter were set by Liat Grayver. e-David then generated stroke patterns according to these parameters and realized them on canvas. The two paintings are also included in the final painting of our other project “Homage to Jackson Pollock”: One painting is hanging on the wall in the painting, the other one is lying on the floor.
Link to our page at robotart.org: https://robotart.org/team/profile/e-david/
Liat Grayver: https://www.liatgrayver.com/liat-grayver-about
This gallery contains 8 photos.
The work of e-David and Liat Grayver was exhibited at Fresh Paint 9
Our small e-David was shown a the Exhibition “Pinselstriche im Digitalen Zeitalter” in Halle 14 Leipzig.
e-David is taking part in the robotart competition. We submitted a portrait painting of Isaac Asimov. Visit http://robotart.org/ and vote for e-David if you like it!
In January a group of artists and students from the MIT visited the
Computer Graphics Group (Prof. Deussen) and evaluated the e-David
painting robot (see www.e-david.org) for different methods of painterly
abstraction. With our painting robot we want to mimic human artists and
find out to which extent painting processes can be performed by
machines. Part of our project is research on computational creativity:
we want to research and develop methods in which the machine starts to
develop its own painting strategies and styles. The machine should be
able to learn from past paintings when producing new ones. Another
important aspect is quantification of abstraction. We want to develop
styles in which we can predict and maintain a wanted degree of
abstraction, technically (number of strokes) and also perceptually.
The MIT students want to use the machine in a semi-automatic way and
combine human and machine painting. Ideally the human would only direct
the system by sketching and giving hints for the style to be used. Then
the machine does the often cumbersome painting work. At the end the
human finishes the artwork. Benjamin Tritt (http://bentritt.com) is a
well-know American Artist that combines classical painting styles with
modern motives. He is interested in machine painting since large-scale
artworks are very time-consuming and robots might be very helpful in
creating intermediate painting layers.