pix2code: Generating Code from a Graphical User Interface Screenshot

Code

• github.com/tonybeltramelli/pix2code
  OfficialIn papernone★ 0
• github.com/pranayanand123/Design2Code
  none★ 0
• github.com/badaro48/documents
  none★ 0
• github.com/RAHUL-KESHERVANI/my_pix2code
  none★ 0
• github.com/kevinleewy/pytorch_pix2code
  pytorch★ 0
• github.com/ThomasVandendijk/capita_selecta_pix2code
  none★ 0
• github.com/steve-levesque/Portfolio-AI-DesignToCode
  none★ 0
• github.com/Atharva-Phatak/Generating-Webpages-from-Screenshots
  pytorch★ 0
• github.com/sruthisripathi/ui2c
  none★ 0
• github.com/ZvezdocheTag/variable-ui
  none★ 0

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).

Tasks

Reproductions