pix2code: Generating Code from a Graphical User Interface Screenshot

Anonymous

Abstract: Transforming a graphical user interface screenshot created by a designer into computer code is a typical task conducted by a developer in order to build customized software, websites, and mobile applications. In this paper, we show that deep learning methods can be leveraged to train a model end-to-end to automatically generate code from a single input image with over 77% of accuracy for three different platforms (i.e. iOS, Android and web-based technologies).

TL;DR: CNN and LSTM to generate markup-like code describing graphical user interface images.

Keywords: computer vision, scene understanding, text processing

Community Implementations: [ 10 code implementations](https://www.catalyzex.com/paper/arxiv:1705.07962/code)

Withdrawal: Confirmed