26TH INTERNATIONAL CONFERENCE ON ENGINEERING AND PRODUCT DESIGN EDUCATION - COMPARING UNDERSTANDABILITY OF HAND SKETCHES VERSUS AI-GENERATED RENDERS FOR PRODUCT DESIGN

Oct 24, 2026

Sketching to communicate design ideas is a key step in the product design process, yet generative AI tools are increasingly used at the concept stage. This study evaluates whether an AI sketch tool (Vizcom), which generates rendered images from sketch inputs, improves the understandability of students’ design concepts. In an undergraduate engineering and product design course, hand-drawn concepts and Vizcom renders were rated separately with standardized rubrics. Results show no significant difference in overall understandability, though sketch quality traits correlate with render proportionality and understandability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Abstract

1 Introduction

2 Backgrounds

2.1 The role of design sketching in the design process

2.2 Generative AI in design

26TH INTERNATIONAL CONFERENCE ON ENGINEERING AND PRODUCT DESIGN EDUCATION 5-6 SEPTEMBER 2024, ASTON UNIVERSITY, BIRMINGHAM, UNITED KINGDOM COMPARING UNDERSTANDABILITY OF HAND SKETCHES VERSUS AI-GENERATED RENDERS FOR PRODUCT DESIGN Kristin BARTLETT, Jonathan MILLS and Carly HAGINS University of Kentucky, United States of America ABSTRACT 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 AIbased 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. Keywords: Artificial Intelligence, product design, design education, design sketching, understandability 1 INTRODUCTION This paper describes an application of generative artificial intelligence (AI) to student work in a collaborative undergraduate design course. We describe an initial quantitative comparative analysis of a set of concept sketches generated by hand using digital sketching software (most students used Procreate with an Apple pencil on an iPad), and the analogous concept images generated using an AIbased tool called Vizcom. Vizcom software pairs a visual interface with a text-based input and is designed to create high-quality rendered images from a combination of sketch and text input. The primary aim of this analysis was to investigate whether Vizcom helped the students communicate their ideas more clearly than hand sketches. As far as we are aware, there is not yet any published work exploring the effectiveness of using AI to help designers represent their ideas at the concept sketching stage. Artificial intelligence tools are likely to change the way product designers sketch, and the present work aims to investigate how. 2 BACKGROUNDS 2.1 The role of design sketching in the design process Design sketches used at different phases of the design process have different roles, and sketching is treated differently in engineering design and product/industrial design. In product design, ideation sketches are used to explore a wide variety of ideas and/or variations of the same idea. These sketches are typically looser and may resemble ‘doodles’or ‘thumbnails’ [1] . Concept sketches are more detailed than ideation sketches and begin to explore more technical solutions and feasible ideas [1]. Presentation sketches are more detailed and realistic than concept sketches and are typically presented to a client or external audience to provide a clear and inspiring image of what the final product could look like [1] . In engineering design education, artistic sketching skills are not as highly emphasized. While sketching is EPDE2024/1170 fundamental to design brainstorming and documenting ideas, engineering and technology education place little emphasis on the instruction o

FAQs

What is the primary goal of the study?

To determine whether an AI-based sketch tool (Vizcom) improves the understandability of students’ design concepts compared with hand sketches.

How were the sketches and AI renders evaluated?

They were rated separately using standardized rubrics, based on assessed characteristics of the hand sketches and corresponding render outputs.

What did the results indicate about understandability?

There was no significant difference in understandability between hand sketches and AI-generated renders, while certain sketch characteristics correlated positively with render proportionality and understandability.

Oct 24, 2026

Upload by Mary Man