COMPARING UNDERSTANDABILITY OF HAND SKETCHES VERSUS AI-GENERATED RENDERS FOR PRODUCT DESIGN

Sketching to communicate design ideas is an important step in the design process. Image-generative artificial intelligence (AI) tools are increasing in prevalence and popularity, some of which focus specifically on sketch-based inputs. The primary aim of this study was to investigate whether an AI-based sketch tool would improve the understandability of students' design concepts. In the context of an undergraduate engineering and product design course, we introduced Vizcom, an AI tool which uses sketch-based inputs to generate renders. In this paper, we describe a quantitative analysis of a dataset of students' hand drawn concepts and the resulting Vizcom render outputs. The sketches and renders were rates separately using standardized rubrics. Our analysis of these ratings indicated that there was no significant difference in understandability between the hand sketches and the AI-generated renders. The characteristics of the hand sketches: line quality, proportionality, and understandability, were all positively correlated with the proportionality and understandability of the AI-generated renders. Our results suggest that the use of Vizcom did not reduce the need for strong hand-sketching skills in communicating design concepts, but Vizcom may offer some benefits in quickly conveying realistic materials and contexts. Results may be different for other types of design concepts and other populations.