Exploring UI Design‑to‑Code Automation: Practices from Meituan, Xianyu, Microsoft and Large‑Model Flutter Generation

This article surveys recent advances in automatically converting UI design drafts into code, reviewing solutions from Meituan, Xianyu, Microsoft, a range of design‑to‑code tools, Flutter‑specific generators, JD's Ling platform, and practical experiments with large language models for Flutter code generation.

Design AutomationFlutterTooling

0 likes · 7 min read

Exploring UI Design‑to‑Code Automation: Practices from Meituan, Xianyu, Microsoft and Large‑Model Flutter Generation

Xianyu Technology

Dec 11, 2019 · Artificial Intelligence

Improving Small Object Detection for UI2CODE via Data Augmentation and Model Optimization

The study enhances UI2CODE’s ability to detect tiny UI components by augmenting training data with copied small objects, upgrading the detector from Faster RCNN to FPN and Cascade FPN, and refining box positions with smoothing and projection, achieving superior small‑object mAP/mAR and enabling broader UI parsing applications.

Computer VisionFPNModel Optimization

0 likes · 9 min read

Improving Small Object Detection for UI2CODE via Data Augmentation and Model Optimization

Xianyu Technology

Jun 5, 2019 · Mobile Development

UI2CODE Page Framework: Evolution and Architecture

The UI2CODE Page Framework evolves a unified, MVP‑based architecture—comprising Pages, Cards, and Reactions—that leverages AI‑driven code generation and Redux messaging to enable high‑cohesion, low‑coupling components, dramatically cut development time, and plans further AI integration for fully automatic page creation.

AI code generationFlutterMobile Development

0 likes · 8 min read

UI2CODE Page Framework: Evolution and Architecture

Xianyu Technology

Feb 27, 2019 · Artificial Intelligence

UI2CODE: Layout Analysis and Background/Foreground Extraction for UI Images

The UI2CODE system tackles UI layout analysis by first extracting backgrounds with Sobel, Laplacian and Canny edge detection plus a flood‑fill algorithm, then isolating foreground components through connected‑component analysis and a Faster R‑CNN classifier, and finally fusing both pipelines to achieve superior precision, recall and IoU on Xianyu app screenshots.

Computer VisionDeep LearningFaster R-CNN

0 likes · 16 min read

UI2CODE: Layout Analysis and Background/Foreground Extraction for UI Images

iQIYI Technical Product Team

Dec 28, 2018 · Artificial Intelligence

AI‑Driven Visual Automation Testing Frameworks: Challenges, Opportunities, and the Aion Solution

The article examines shortcomings of traditional visual automation frameworks—weak cross‑platform support, ID dependence, and fragile screenshot matching—and shows how Aion’s hybrid approach, merging image‑processing segmentation with deep‑learning classification and OCR, delivers a more stable, cross‑platform, “visible‑to‑obtain” testing solution while acknowledging remaining accuracy challenges.

AI testingOCRUI2Code

0 likes · 11 min read

AI‑Driven Visual Automation Testing Frameworks: Challenges, Opportunities, and the Aion Solution

Xianyu Technology

Dec 18, 2018 · Frontend Development

UI Semantic Parsing: From Image to Code with AI

The UI semantic parsing system uses NLP and YOLO‑based image recognition combined with rule‑based reasoning to automatically translate design images into readable Vue code, assigning semantic classes to elements, inferring layout hierarchies, and enabling data binding, thus bridging the gap between designers and front‑end developers.

Front-end AutomationNLP analysisUI semantic parsing

0 likes · 9 min read

UI Semantic Parsing: From Image to Code with AI