GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks
Tianming Zhao, Chunyang Chen, Yuanning Liu, Xiaodong Zhu
Abstract
Graphical User Interface (GUI) is ubiquitous in almost all modern desktop software, mobile applications and online websites. A good GUI design is crucial to the success of the software in the market, but designing a good GUI which requires much innovation and creativity is difficult even to well-trained designers. In addition, the requirement of rapid development of GUI design also aggravates designers' working load. So, the availability of various automated generated GUIs can help enhance the design personalization and specialization as they can cater to the taste of different designers. To assist designers, we develop a model tool to automatically generate GUI designs. Different from conventional image generation models based on image pixels, our tool is to reuse GUI components collected from existing mobile app GUIs for composing a new design which is similar to natural-language generation. Our tool is based on SeqGAN by modelling the GUI component style compatibility and GUI structure. The evaluation demonstrates that our model significantly outperforms the best of the baseline methods by 30.77% in Fr'echet Inception distance (FID) and 12.35% in 1-Nearest Neighbor Accuracy (1-NNA). Through a pilot user study, we provide initial evidence of the usefulness of our approach for generating acceptable brand new GUI designs.