Evaluating an Artificial Intelligence Approach for Converting Sketches to UI Layouts
Bibliographic record
Abstract
User Interface (UI) Designers often rely on hand-drawn sketches during the design process for their flexibility, despite the availability of digital tools.However, converting these sketches to high-fidelity layouts can be time-consuming and complicated.To address this challenge, Artificial Intelligence (AI) and Machine Learning (ML) methods have been developed to assist designers.This study evaluated the effectiveness of AIpowered tools that convert hand-drawn sketches into high-fidelity layouts via UIzard's Scan Wireframe Sketch function, in terms of reducing time consumption and complexity.Fifteen participants were tasked with designing UI layouts using the AI agent to convert their sketches to editable layouts.The study found that implementing an AI tool did not reduce the duration of the UI design process and may have even prolonged it due to the tool's performance and unfamiliar functionalities, as well as personal factors of the participants.However, the tool could indirectly reduce the time consumption of designers' workflow through their non-designer colleagues.The study also found that the tool reduced complexity in UI designers' work process to some extent, which could be attributed to the tool's functionalities and participants' personal factors such as sketching experience and expectations.This study adds to the knowledge of human-AI collaboration in the design space and provides suggestions for AI-powered tools that convert hand-drawn sketches into UI layouts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.052 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".