Pollock – Harvard scientists reproduce drip-paint technique using AI and 3D printers

Can a machine be taught to paint like Jackson Pollock? More precisely: Can 3D printing utilize Pollock 's special techniques to print complex forms quickly and precisely?

According to a group of researchers at Harvard University, it is possible. They combined artificial intelligence and physical principles to develop an innovative 3D printing technique that imitates an artist's unique paint-spraying style

Although their main goal is not to create a Pollock-like print using computer algorithms, they strive to produce complex shapes at a faster pace.

Pollock and his unique drip-paint technique

Pollock was a famous representative of abstract expressionism and best known for his drip painting technique (also action painting ). Instead of applying paint with a brush, he dripped it onto his works from above or flung it onto the canvas over a large area.

This process is pretty much the opposite of 3D printing, where the material to be printed is applied layer by layer with millimeter precision and from a very short distance to avoid instabilities.

Harvard researchers combine physics and machine learning to use Pollock's drip-paint technique for fast and precise 3D printing

This likely made the challenge all the greater for the Harvard research team led by the Indian-American mathematician and biologist Lakshminarayanan Mahadevan.

I wanted to know if it was possible to emulate Jackson Pollock and reverse-engineer what he did.”

L. Mahadevan , the Lola England de Valpine Professor of Applied Mathematics at the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS), and Professor of Organismic and Evolutionary Biology as well as Physics in the Faculty of Arts and Sciences (FAS) , comments. The renowned researcher is also the director of the Soft Math Lab at Harvard.

Mahadevan and his team (Gaurav Chaudhary, Stephanie Christ, A. John Hart)  combined physics and machine learning to develop a new 3D printing technique that can quickly create complex physical patterns – including replicating a section of a Pollock painting –by harnessing the same natural fluid instability that Pollock used in his work.

The research was published in Soft Matter .

Algorithm deciphers Jackson Pollock and the fluid dynamics of viscous materials

Mathematically calculating the behavior of a liquid substrate under motion and gravity was a challenging task. The goal was to give the 3D printer appropriate instructions based on these calculations.

However, it was anything but simple, as there were many variables such as density, viscosity, and altitude that had to be taken into account. An essential source of inspiration was Mahadevan's earlier work on the fluid dynamics of honey . According to a report by heise online , this research explained , among other things, how Jackson Pollock was able to apply his paint precisely despite his seemingly chaotic method.

The fully developed printer in action painting–action in the following video:

Results close a gap in modern 3D and 4D printing processes

Modern 3D and 4D printing methods circumvent the problem of unstable fluid flow by positioning the nozzle a short distance from the surface and moving it along a defined path from point A to point B, the research team explains.

This approach works well, but the process can be slow due to the need to apply ink or other printing materials at every point along the path. Furthermore, the proximity of the nozzle to the surface limits creative freedom, as natural fluid instabilities cannot be tolerated and must be avoided.

Pollock's approach of throwing paint from a great height meant that even if his hand moved along a certain trajectory, the paint would not follow that trajectory due to the acceleration caused by gravity

Gaurav Chaudhary explains . The former postdoctoral researcher at the Harvard School of Engineering and Applied Sciences and lead author of the study emphasized the importance of this technique in an interview:

Even the slightest movement can lead to significant ink splatter. Using this method, it's possible to print longer distances than one could actually move, as gravity provides free acceleration

This innovation thus allows for greater flexibility in the printing process.

To what extent the researchers or participants will now use the developed printing technique to create their own art in the style of Pollock and thus carry on his artistic legacy remains unknown… 😉

Joachim Rodriguez y Romero

Owner and Managing Director of Kunstplaza . Publicist, editor, and passionate blogger in the fields of art, design, and creativity since 2011. Graduated with a degree in web design from university (2008). Further developed creative techniques through courses in freehand drawing, expressive painting, and theatre/acting. Profound knowledge of the art market gained through years of journalistic research and numerous collaborations with key players and institutions in the arts and culture sector.

www.kunstplaza.de

You might also be interested in:

A look at: Jackson Pollock From idea to reality: How 3D modeling with AI generators opens up new avenues for artists Why artificial intelligence (AI) cannot (yet) replace human artists Abstract photography – motifs beyond reality State of Digital Art 2025: What is the status of NFTs, AI art & Web3 in the art world