Martin Fuchs’s research while affiliated with Stuttgart Media University and other places

We review recent methods in 2D creative pattern generation and their control mechanisms, focusing on procedural methods. The review is motivated by an artist's perspective and investigates interactive pattern generation as a complex design problem. While the repetitive nature of patterns is well‐suited to algorithmic creation and automation, an artist needs more flexible control mechanisms for adaptable and inventive designs. We organize the state of the art around pattern design features, such as repetition, frames, curves, directionality, and single visual accents. Within those areas, we summarize and discuss the techniques' control mechanisms for enabling artist intent. The discussion includes questions of how input is given by the artist, what type of content the artist inputs, where the input affects the canvas spatially, and when input can be given in the timeline of the creation process. We categorize the available control mechanisms on an algorithmic level and categorize their input modes based on exemplars, parameterization, handling, filling, guiding, and placing interactions. To better understand the potential of the current techniques for creative design and to make such an investigation more manageable, we motivate our discussion with how navigation, transparency, variation, and stimulation enable creativity. We conclude our review by identifying possible new directions that can inspire innovation for artist‐centered creation processes and algorithms.

Decorative ornamentation involves a careful balance between accent and order. Existing techniques leave artists either with tedious manual processes or the uncontrolled automatic generation of rather homogeneous patterns that lack creatively-placed visual highlights. We present a method to close this gap, offering the control and quality of manual creation, and the efficiency and accuracy of computation. At the core of our system, customizable and modularly combinable element placement functions fill a space automatically under global design constraints. We provide a set of example placement functions that implement order based on design principles for ornamentation such as balanced element distribution and symmetry. To create structural hierarchies and to guide an ornament to the space it fills, we allow artists to direct the connectivity of elements with drawn strokes. Artists can also draw guides to create vector fields, which organize the ornament along streamlines. Path planning automatically routes around obstacles while aligning the ornament to their borders. Our method combines high-level control mechanisms like taking guidance from example images to low-level control like placing single elements as visual accents and making local edits within the computed ornament. By automating tedious tasks and offering familiar input mechanisms like drawing, we enable artists to focus on the creative intent.