Abstract

Visual synthesis methods, such as sketch-based visual migration models, can generate creative inspiration while visually characterizing the target object. However, the cognitive impact and design performance of synthetic-sketches have received limited attention. This study examines the effectiveness of using synthetic-sketches generated through a visual migration model (Cycle-GAN) as a conceptual support tool in the early design phase. We aimed to understand its strengths by inviting 24 master's students with design backgrounds and digital drawing experience to experiment. The students were divided into two groups: one using synthetic-sketches and the other using product renderings as inspirational stimuli. Results indicated that the group using synthetic-sketches refined original concepts more deeply during concept generation and spent less time on conceptual innovation compared to the group using product renderings. This was attributed to the design behavior of modifying visual features and the perception that synthetic-sketches help test and refine concepts. Synthetic-sketches seem particularly suited to the later stages of individual sketching, aligning with the designer's reconstruction process. This study highlights the potential of synthetic-sketches supported by visual migration models as valuable tools in the early design phase. Further research could explore their wider application and strategies to maximize benefits.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.