Toward Modeling Creative Processes for Algorithmic Painting
This work addresses the challenge of incorporating human-like creativity into algorithmic painting systems, though it appears incremental as it builds on existing computational art concepts.
The paper tackles the problem of modeling creative processes in algorithmic painting by identifying two key components from human artistic practice: vague high-level goals and exploratory idea discovery. It proposes computational mechanisms including underspecified loss functions and iterative painting procedures with task decompositions to imitate these elements.
This paper proposes a framework for computational modeling of artistic painting algorithms, inspired by human creative practices. Based on examples from expert artists and from the author's own experience, the paper argues that creative processes often involve two important components: vague, high-level goals (e.g., "make a good painting"), and exploratory processes for discovering new ideas. This paper then sketches out possible computational mechanisms for imitating those elements of the painting process, including underspecified loss functions and iterative painting procedures with explicit task decompositions.