EvoDesigner: Towards Aiding Creativity in Graphic Design

Published: 01 Jan 2022, Last Modified: 14 Nov 2024EvoMUSART 2022EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Graphic Design (gd) artefacts aim to attract people’s attention before any forward objectives. Thus, one of the goals of gd is frequently finding innovative aesthetics that stand out over competing design artefacts (such as other books covers in a store or other posters on the street). However, as gd is increasingly being democratised and broadly shared through social media, designers tend to adopt trendy solutions, lacking disruptive and catchy visual features. EvoDesigner aims to assist the exploration of innovative graphic design solutions by using an automatic evolutionary approach to evolve the design of a number of text, shapes, and image elements inside two-dimensional canvases (pages). To enable the collaboration human-machine, the process has been integrated into Adobe inDesign, so human designers and EvoDesigner may alternately edit and evolve the same design projects, using the same desktop-publishing software. In this paper, an overview of the proposed system is presented along with the experimental setup and results accomplished so far on an evolutionary engine developed. The results suggest the viability of the development made in this first iteration of the system, which aims to reinterpret existing layouts in an unexpected manner.
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview