Abstract:

Recent advances in artificial intelligence (AI) tools have substantially expanded the possibilities for transforming hand drawn sketches and photographs into refined digital representations. In engineering education, and especially focusing on courses related to graphical expression, these capabilities offer new pathways for supporting students as they transition from manually produced figures to structured digital formats that can be further edited, stylised, or adapted to the requirements of different assignments.

This work presents a comparative map of AI supported workflows for image conversion and demonstrates, through engineering oriented examples, how such workflows can facilitate activities such as conceptual sketching, technical diagramming, product ideation, and the preparation of structured visual assets for reports and presentations.

The study examines the use of both generalist AI generators (Gemini, Copilot, ChatGPT) and specialised platforms (Adobe Firefly, PixelBin, PhotosStyle, blieve.ai, NewArc.ai), discussing their respective strengths, limitations, access requirements, and credit models. Particular emphasis is placed on the importance of prompt engineering, the learning curve associated with different tools, and the necessity of manual post processing for obtaining technically accurate results. Additionally, the paper explores the use of AI to convert photographs of components, machines, assemblies, and technical setups into schematic or illustrative formats, a transformation that is highly valuable in engineering contexts such as the creation of instruction manuals, maintenance guides, and simplified visual documentation.

A qualifying table for evaluating the quality, visual semantic fidelity, and pedagogical utility of the generated images is proposed. The article concludes by providing practical guidelines for engineering instructors seeking to integrate AI based image conversion into courses on graphical communication and related subjects and outlines future research directions aimed at understanding the impact of these tools on students’ cognitive load and perceived learning.

Keywords:

AI support, technical draw, engineering.