pix2code: Generating Code from a Graphical User Interface Screenshot
Tony Beltramelli

TL;DR
This paper presents a deep learning approach that automatically generates code from GUI screenshots with over 77% accuracy across iOS, Android, and web platforms, streamlining the development process.
Contribution
It introduces an end-to-end deep learning model capable of converting GUI images into code, a novel application in automated UI code generation.
Findings
Achieved over 77% accuracy in code generation
Effective across three platforms: iOS, Android, web
Demonstrated feasibility of deep learning for UI-to-code conversion
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).
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
AI Learns To Create User Interfaces (pix2code) | Two Minute Papers #161· youtube
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Multimodal Machine Learning Applications · Video Analysis and Summarization
