Magic Layouts: Structural Prior for Component Detection in User Interface Designs

TL;DR

Magic Layouts introduces a structural prior for UI component detection that improves parsing accuracy of screenshots and sketches by leveraging learned spatial relationships, aiding rapid UX prototyping.

Contribution

The paper develops a method to incorporate learned structural priors into UI component detectors, enhancing robustness and accuracy in layout parsing.

Findings

Performance gains on UI layout parsing tasks

Effective detection of buttons and text boxes in sketches and screenshots

Facilitates rapid digital prototyping of UX designs

Abstract

We present Magic Layouts; a method for parsing screenshots or hand-drawn sketches of user interface (UI) layouts. Our core contribution is to extend existing detectors to exploit a learned structural prior for UI designs, enabling robust detection of UI components; buttons, text boxes and similar. Specifically we learn a prior over mobile UI layouts, encoding common spatial co-occurrence relationships between different UI components. Conditioning region proposals using this prior leads to performance gains on UI layout parsing for both hand-drawn UIs and app screenshots, which we demonstrate within the context an interactive application for rapidly acquiring digital prototypes of user experience (UX) designs.